1

MGT 526: RESEARCH METHODOLOGY

UNIT 1: BUSINESS RESEARCH
Definition/ Meaning
Business research is a process of acquiring detailed information of all the areas of business
and using such information in maximizing the sales and profit of the business. Such a study
helps companies determine which product/service is most profitable or in demand. In
simple words, it can be stated as the acquisition of information or knowledge for
professional or commercial purposes to determine opportunities and goals for a business.

Business research can be done for anything and everything. In general, when people speak
about business research it means asking research questions to know where the money can
be spent to increase sales, profits or market share. Such research is critical to make wise
and informed decisions.

Meaning:

The business demands that managers and researchers work towards a goal-whether
immediate or futuristic, else the research ceases to have significance in the field of
management. The fundamental value of business research is that it curtails uncertainty by
providing information that improves the decision-making ability. It identifies problems or
opportunities, selects and implements a course of action and evaluates the adopted course
of action.

NATURE OF BUSINESS RESEARCH:

I. Business Research helps you communicate with current and potential customers in a
better way.
II. It helps you identify opportunities and threats in the marketplace.
III. It helps you minimize risks.
IV. Business research is used to plan investments and financial outcomes effectively.
V. It helps you build a better market position.
VI. It can keep you updated with current trends and innovations in the market.

SCOPE OF BUSINESS RESEARCH:

1
 2

i. Production Management: The research performs an important function in product

development, diversification, introducing a new product, product improvement, process
technologies, choosing a site, new investment etc.

ii. Personnel Management: Research works well for job redesign, organization
restructuring, development of motivational strategies and organizational development.

iii. Marketing Management: Research performs an important part in choice and size of
target market, the consumer behavior with regards to attitudes, life style, and influences of
the target market. It is the primary tool in determining price policy, selection of channels of
distribution and development of sales strategies, product mix, promotional strategies, etc.

iv. Financial Management: Research can be useful for portfolio management, distribution
of dividend, capital raising, hedging and looking after fluctuations in foreign currency and
product cycles.

v. General Management: It contributes greatly in developing the standards, objectives,

long-term goals, and growth strategies.

IMPORTANCE / NEED OF BUSINESS RESEARCH:

i. Business research helps businesses understand their customers’ buying patterns,

preferences and pain points, gain deeper insights into the contenders, current market trends,
and demographics.

ii. Using effective strategies to understand the demand and supply of the market,
businesses can always stay ahead of the competition

. iii. Using business research, they can reduce costs and design solutions that aim at the
market demand and their target audience.

iv. Chances of failures are less with business research as it gives an idea of the target
customers and the perfect time to launch a product.

v. Research is the building block of any business. It acts as a catalyst to thrive in the
market. So, never underestimate the value of market research and leverage its benefits to
give an extra edge to your business.

Managerial value of Business Research

3
 4

Research as the application of scientific method,

The Scientific method is a process with the help of which scientists try to investigate,
verify, or construct an accurate and reliable version of any natural phenomena. They are
done by creating an objective framework for the purpose of scientific inquiry and analyzing
the results scientifically to come to a conclusion which either supports or contradicts the
observation made at the beginning.

Scientific Method Steps

The aim of all scientific methods is the same, that is, to analyze the observation made at the
beginning but there are various steps adopted as per the requirement of any given
observation. However, there is a generally accepted sequence of steps of scientific methods
1. Observation and formulation of a question: This is the first step of a scientific
method. In order to start one, an observation has to be made into any observable
aspect or phenomena of the universe and a question needs to be asked pertaining to
that aspect. For example, you can ask, “Why is the sky black at night? or “Why is air
invisible?”
2. Data Collection and Hypothesis: The next step involved in the scientific method is
to collect all related data and formulate a hypothesis based on the observation. The
hypothesis could be the cause of the phenomena, its effect, or its relation to any other
phenomena.
 5

3. Testing the hypothesis: After the hypothesis is made, it needs to be tested

scientifically. Scientists do this by conducting experiments. The aim of these
experiments is to determine whether the hypothesis agrees with or contradicts the
observations made in the real world. The confidence in the hypothesis increases or
decreases based on the result of the experiments.
4. Analysis and Conclusion: This step involves the use of proper mathematical and
other scientific procedures to determine the results of the experiment. Based on the
analysis, the future course of action can be determined. If the data found in the
analysis is consistent with the hypothesis, it is accepted. If not, then it is rejected or
modified and analyzed again.
It must be remembered that a hypothesis cannot be proved or disproved by doing one
experiment. It needs to be done repeatedly until there are no discrepancies in the data and
the result. When there are no discrepancies and the hypothesis is proved beyond any doubt,
it is accepted as a ‘theory’.
Importance of research in managerial decision making;

It is an established fact that research assists in business decisions and further in different
functional areas of management. Business managers in human resources, production,
marketing or finance regularly face situations that require effective and actionable decision
making. Most of these decisions require additional information which can best be addressed
by research.

1. Marketing

Is one of the areas of business where research is

the lifeline. It is carried out on a wide variety of
topics and is conducted by the organization as
well as outsourced to research agencies. Broader
industry or product-category specific studies are
also carried out by market research agencies
which assist in business decisions. There are
various issues which require attention for research
including market potential analysis, market
segmentation, demand estimation, market
structure analysis and business trend analysis. An
organization also carries out research related to
product, pricing, promotion and place. These days
 6

with the increase in competition and the need to retain customers, customer relationship
management, satisfaction, and loyalty have been added to the areas in which significant
research is being carried out.

2. Human Resource Management

Human resource management and organizational behavior involve basic research as a lot of
academic and macro level research may be adapted and implemented by organizations into
their programs and policies. Applied HR research is more predictive and solution oriented.
There are a number of academic and organizational areas which attract more research. Such
areas include performance management, organizational climate, talent and aptitude
analysis, organizational change management, employee selection and staffing,
organizational planning and development, job analysis, performance appraisal, recognition
and reward studies, compensation analysis, training and development, employee
relationship analysis, negotiation and wage settlement, turnover and attrition and work life
balance studies.

Critical success factor analysis and employer branding are some emerging areas in which
HR research is being carried out.

3. Financial and accounting research

Marketing Research HRM Research Financial & Accounting Research Production & OM
Research Cross Functional Research The area of financial and accounting research is so
vast that it is difficult to provide a framework of the research areas. However, there are
some prevalent research issues including asses pricing, corporate finance, capital markets,
takeovers and mergers, financial reporting, the impact of factors on returns, financial
derivatives, credit risk modeling, corporate decision-making analysis, investment risk
appraisal, analysis of corporate financial reporting behavior, accounting based values,
evaluation and usage of accounting information by investors and evaluation of management
compensation schemes, analysis of audit regulations, analysis of audit methodologies,
corporate governance, accountability of audit committees, risk estimation and analysis,
business policy and merchant banking.

4. Production and operation management

Production and operation management is the area of research which quantifies

implementation of the research results on huge cost and process implications. Research in
this area is highly focused and problem analysis specific. The decision areas in which
research studies are carried out include product/service design and development, resource
allocation and capacity planning, demand forecasting and decision analysis, production
 7

scheduling and material requirement management, work design planning and monitoring,
project management and maintenance management studies, logistics and supply chain and
inventory management analysis, quality estimation and assurance studies including total
quality management and quality certification analysis, just in time technology and
economic order quantity are topics adapted by organizations for optimizing operations.

5. Cross functional research

Since business management is an integrated amalgamation of all these and other areas
sometimes requires a unified thought and approach to research. These studies require an
open orientation where experts from across the disciplines contribute to and gain from the
study. For example, an area such as new product development requires the commitment of
the marketing, production and consumer insights team to exploit new opportunities. Other
areas requiring cross-functional efforts are corporate governance and ethics, technical
support systems, enterprise resource planning systems, knowledge management, data
mining and warehousing are integrated areas requiring research on managing coordinated
efforts across divisions.

The Research Process

Research, as a tool for progress, satisfies mankind’s curiosity to lots of questions. Whether
you are a high school or college student, you have to take research subject for you to be
able to receive your diploma. To ease your burden in doing research, here are the seven
steps in the research process:

1. Identification of a research problem

Good research always starts with a good problem. You
can observe people or things, visit places, read print
materials, or consult experts to find the research problem
that is right for you. The research problem guides you in
formulating the hypothesis and interpretation of your
findings so that you can formulate the right conclusion. A
good research problem is important because it is the basis
of all subsequent research activities you are going to
undertake. Factors like area of interest, availability of
funds, socio-economic significance of the study, and the
safety measures to be undertaken should be considered in
finding a good research problem.
 8

2. Developing Research Design

The research design is the plan of action for accomplishing objectives and answering the
research question. The availability of a large number of methods, techniques, procedures,
protocols and sampling plans may complicate the choice of a research design. For example,
a researcher may determine for a secondary data study, case study, survey, experiment, or
simulation. If a survey design is selected, it needs to be determined whether it should be
administered by mail, computer, telephone or personal interview, all relevant data is
collected at one time or at regular intervals, the kind of structure of the questionnaire or the
qualifications interview guide should possess, the wording of the questions employed and
the scaling of the responses open-ended or closed ended, the means of achieving the
reliability and validity of the measures. It is also to be determined whether the
characteristics of the interviewer will influence responses to the measurement questions, the
kind of training the data collectors should receive, a sample or a census is to be taken, the
type of sampling to be considered. These issues represent only a few of the decisions to be
made when just a single method is selected.

3. Sampling Design
Next step in formulating the design is to identify the target population and select the sample
if a census is not taken up for study. The researcher must decide how many people to
interview and who the respondents will be; number of events to observe; or the number of
records to inspect. A sample is a representative portion of the target population. When
researchers undertake sampling studies, they usually estimate population values and test
statistical hypotheses. The sampling process must ensure that every element of the
population target finds the same probability of selection if probability sampling is applied.
In case of non-availability of an alternative, a non-probability sampling may be applied.

4. Collection of Data
The collection of data may take place from a simple observation at one location to an
important survey of multinational corporations in different countries. The method selected
will determine the method of data collection. Questionnaires, standard tests, observational
forms, laboratory notes, and instrument calibration logs are among the devices applied to
record raw data. A researcher has to plan for collection of secondary data, primary data or
both, as may be required. Primary data provides the original information for purposes
whereas secondary data consists of information that has already been collected. The
researcher would either select one of the methods or both depending on the nature of the
study, the objectives of the study, availability of financial resources, availability of time
 9

available and the desired degree of accuracy required. Primary data can be collected
through experiment or survey method. If the researcher performs an experiment, he needs
some quantitative measurements, the data with which he investigates the relationship
contained in the research hypothesis. But in the case of a survey, data can be collected by
either one or more methods out of questionnaire, telephonic or personal interview and
observation methods.

5 Analysis of Collected Data

Raw data are exceptionally useful for making management decisions, Managers require
information. Researchers create information by data analysis involving reduction of
accumulated data to a manageable size, making summaries, searching for patterns, and
employing statistical techniques. Scaled responses on questionnaires and experimental
instruments often demand the analyst to obtain various functions, and relationships among
variables. Further, researchers need to interpret these findings in the light of the research
questions and check the consistency of the results with respect to hypotheses and theories.
The data analysis involves different steps including coding, editing, tabulation, analysis,
and interpretation.

6. Preparation of Research Report

Ultimately, it is essential to prepare a report and convey the findings and
recommendations to the manager for the purpose of decision-making. The organization of
the report and the style of writing differ according to the targeted audience, the juncture and
purpose of the research. The results of applied research may be communicated in a
conference call, a letter, a written report or an oral presentation and at occasion all of
them. The design, sampling plan and statistical techniques for analyzing the data assist to
establish the researcher’s credibility. Thus, the researcher must exactly evaluate the
manager’s needs throughout the research process and incorporate this understanding in the
final product, the research report. Taking the objectives of the study into consideration, the
researcher should make the study report. The findings should be written in a concise,
simple and objective-oriented manner. At a minimum, a research report should contain
these sections: An executive summary of synopsis of the problem, findings and
recommendations An overview of the research: background of the problem, literature
summary, methods, procedures and conclusions. Must incorporate a section including
implementation strategies in respect of the recommendations A technical appendix with all
the material necessary to replicate the project
 10

TYPES OF RESEARCH

1. Exploratory Research
The exploratory research goes beyond description and undertakes to explain the reasons
for the phenomenon that the descriptive study merely observed. In such a study, the
researcher makes use of theories or hypotheses to determine the factors that made a
certain phenomenon to occur. Exploratory Research Conclusive Research Descriptive
Research Causal Research The lack of structure and flexibility characterize the research
design for exploratory research. This research design is diagnostic in nature and is
generally used for the development of hypotheses concerning possible problems and
opportunities. Exploratory research provides insight and understanding of the problems.
Exploratory research includes secondary data sources, opinion of experts, surveys, in-
depth discussions, case studies and observations. In most of the times, conclusive
research follows exploratory research for conducting more accurate analysis and
drawing conclusion

2. Conclusive Research
Conclusive research is usually more formal and structured as compared to exploratory
research. Conclusive research is used to supply information for the assessment of
alternative courses of action. This type of research can be subcategorized into (a)
Descriptive research and (b) Casual or experimental research Descriptive research
is used to describe marketing phenomena while attempting to decide the association
among different variables. It also seeks to predict future marketing
phenomena.Conclusive research includes Descriptive research with Cross-sectional or
Time series or Longitudinal or Case studies methods and Causal or experimental
research with the Designs of Experiments.The cross-sectional design particularly
applied in descriptive research, a sample of population elements is taken at one time. In
descriptive research both case study and statistical study can be made use of. Further, in
a longitudinal research design a definite sample of population elements is ascertained
again and again

2.1 Descriptive Research:

Descriptive research is a fact finding investigation aimed at describing the characteristics of
the state of affairs as it exists. It attempts to uncover answers to the questions who, what,
when, where and how. A descriptive study may necessitate collection of data and the
creation of research variables or may involve the interaction of two or more variables, may
 11

or may not have the potential to draw inferences. Business organizations preserving
databases of their employees, customers and suppliers keep significant data to conduct
descriptive studies utilizing internal information. ‘This sort of study is generally admired in
business research because of its versatility across disciplines.’ Across organizations,
descriptive studies create a vast appeal to the managers for planning, monitoring and
evaluating.

2.2 Ex-post facto/ Causal Research

Causal research seeks to reveal cause and affect relations. A good causal research design
seeks to minimize the interference of external variables that is an important part of
marketing research activity of a firm. They are highly structured and need a rigorous
sequential approach to sampling, data collection and data analysis. The design of the study
takes on a critical significance here. To establish a reliable and testable relationship
between two or more constructs or variables, the other influencing variables must be
controlled so that their impact on the effect can be eliminated or minimized. For example,
to study the impact of flexible work policies on turnover intentions, the other intervening
variables, of age, marital status, organizational commitment and job autonomy would need
to be controlled. This kind of research, like pure sciences research, needs experiments to
establish causality. In most of the situations, it is quantitative requiring statistical testing of
the information collected.establish causality. In most of the situations, it is quantitative
requiring statistical testing of the information collected.

Defining the Research Problem

A research problem needs to be identified and clearly defined.

‘The research problem defines the goal of the research in clear terms. Without a clear cut
idea of the goal to be achieved, the research task would become a worthless exercise.
Research like any other human activity is goal directed. ‘It is not always possible for a
researcher to design his problem in a simple, clear and complete manner. He may often
have only a rather general, diffuse, even confused notion of problem. It may even taken an
investigator’s years of exploration, thought and research before he is in a position explicitly
say what queries he has been seeking answers to’

The statement of the problem is one of the most important parts of research. The difficulty
or impossibility in the satisfactory statement of a research problem does not justify that the
 12

researcher ignores the desirability and necessity of stating a research problem. The
fundamental principle is that if one desires to find a solution for a problem, one must well
understand the problem. It can be stated that a larger portion of the solution to a problem
lies in knowing the problem that the researcher is attempting to solve. And the rest lies in
knowing what a problem is.

A good problem statement should possess certain characteristics. One, the problem is
stated in question form. What are the effects on job performance of different types of
incentives? Second, the problem states a relation between variables, in this case between
incentives and job performance. Thus, a problem is stated in an interrogative form or
statement that asks” what relation exists between two or more variables? The answer is
what is being sought in the research. The problem statement relates incentives to job
performance.

There are three features of good problems and problem statements. One, the problem
should show a relation between two or more variables. Second, the problem should be
clearly stated and evidently expressed in question form. Questions have the quality of
posing problems directly. Third, the problem and the problem statement should be such that
they may be empirically tested. A problem that holds implications to be tested its stated
relations is a scientific problem.

Problem Formulation and Statement of Research Problem.

 13

1. Management decision problem

The process of problem identification commences with the identification and the
acknowledging of the difficulty the business manager/researcher is faced with. If the
manager is skilled enough and the nature of the problem requires it to be resolved by
him or her alone, the problem identification process is handled by him or her, else he
or she outsources it to a researcher or a research conducting agency. This stage asks
the author to carry out a problem appraisal, which would involve a comprehensive
audit of the origin and symptoms of the diagnosed business problem.

2. Discussion with subject experts

The next step involves looking at the problem from the right point of view and
holding conversation with industry experts and academic contributors. These persons
have adequate understanding of the industry and the enterprise. These experts may
be available within the company and outside the company. The information on the
present and future scenarios is obtained with the assistance of semi-structured
interviews. Thus, the researcher must have a pre-decided question related to the
uncertainty experienced in problem formulation.

3. Review of literature

A literature review is a comprehensive collection of the information obtained from

both published and unpublished sources of data in the specific area in which the
research is interested including newspapers, journals, reports, magazines,
publications of government and autonomous organizations as well as computerized
databases. The review of literature provides various perspectives and methodologies
available to investigate the problem and identify potential variables that may need to
be investigated.

4. Organizational Context

The industry and the organization data are another important source of formulating
the research problem. If the manager himself is the researcher himself, he might find
it easy to get the data. However, in case the study is outsourced, the detailed
background information of the organization must be compiled, as it serves as the
environmental context in which the research problem has to be defined. In case of
basic research it may not be necessary to give the organizational context where the
study is more generic.

5. Qualitative survey
 14

Sometimes the interview, secondary data and information available within the
organization might not be sufficient to formulate the research problem. In this
situation, an exploratory qualitative survey might be required to get an insight into
the behavioral or perceptual aspects of the problem. These might be based on small
samples and might utilize focus group discussions or pilot surveys with the target
population to assist in disclosing pertinent and topical issues which might have a
significant influence on the problem definition.

6. Management Research problem

The researcher might find the task of identifying all possible dimensions of the
problem to be monumental and impossible. For example, the perception of the
consumer concerning the product, inefficient supply chain, pot holes in the
distribution network, offering from the competitors or ineffective advertising may be
responsible for lack of sales of a new product launch. The researcher has to identify
and refine the most likely reason for the problem and formalize it as the research
problem. Four preliminary investigative steps would be taken to achieve this. The
researcher must be able to isolate the underlying issues from the symptoms of the
problem.

UNIT 2: RESEARCH DESIGN

A research design is a step-by-step approach used by a researcher to conduct a scientific

study. It includes various methods and techniques to conduct research so that a research
problem can be handled efficiently. A researcher has a series of questions that he needs to
find answers by conducting research.

4 Key characteristics of Research Design

a) Neutrality: The results collected in research should be free from bias and neutral.
Discuss and get evaluated your conclusion with experienced multiple individuals and
consider those who agree with your research’s results.

b) Reliability: Research design should be able to ensure the standard results by indicating
how research questions can be formed because a researcher will always want the same
results every time he performs an experiment.
 15

c) Validity: The validity of a research design is used to calculate the expected results and to
estimate the truthfulness of the result. In most cases, researchers opt for their own definition
when it comes to what is considered valid. Therefore, the questionnaire prepared from the
research design is considered valid.

d) Generalization: Generalization is one of the most important key characteristics of

research design. The results obtained from the research should be applicable to a population
and not just to a limited sample.

12 Types of research design

A researcher must have knowledge of various types of research designs to choose which
type of research design should be applied for the research. There are different types of
research designs which are explained below.

1) Case-study design

A case-study research design is used for the in-depth and detailed study of a subject. This
technique is usually used to narrow down a big problem into small discrete, easily researchable
problems.
The case study research design is useful to test the applicability of specific theory or model on
real-life phenomena. A case-study research design is useful in those scenarios where there is
not much information is known or available about the phenomena.
The case-study research design has an important place in various disciplines and professions
such as sociology, political science, clinical science, social science, administrative science, and
psychology.

Advantages of using Case study design

1. The case-study research design delivers a thorough description of the explicit and
rare case.
2. The case-study research design is widely opted by social scientists to test modern
real-life situations and provides an extension of the existing concepts.
3. The case-study research design can modify what is already known through previous
research.
4. It gives the freedom to the researchers to apply various methodologies and include
any number of resources to investigate the problem.
 16

5. The case study research design excels at establishing a relationship between a limited
number of events or conditions and also helps us to understand complex issues.

Disadvantages of using Case-study research design

1. Sometimes research done on a small sample cannot be applied on a large population.
Therefore, a case study research design is difficult to establish reliability and
generalize.
2. The researcher can be biased about the finding of the case because of the intense
exposure to the study.
3. Case study research design does not enable the assessment of cause and effect
relationship.
4. Missing important information can make the case hard to interpret.
5. Sometimes the case may not be the representation of the larger case being
investigated.
6. If research is being done on a specific situation or phenomenon then results might be
applicable to that particular case.

2) Action research design :

The action research design follows a characteristics-based path, where initially an
exploratory stance has opted and understanding is developed about the problem and made
some type of strategies for intervention.
While carrying out the interventions, various forms of relevant observations are collected.
The same path followed again with the new interventional strategies and continued until a
sufficient understanding of the problem was not realized.
The path followed is cyclic or iterative in nature to provide a deeper understanding of the
situation, initializing with hypothesizing and specifying the given problem and moving
ahead making numerous interventions and assessments.

Advantages of using Action research design

1. It is a research design which can be used in work or community situations, because
of its cooperative and adaptive research nature.
2. Action research design focuses on practical and solution-driven research rather than
testing various theories.
3. Action research design increases the chances of learning consciously from their
experience, therefore, it is also viewed as a learning cycle.
4. The Outcomes of the action research design have obvious relevance to practice.
 17

5. No information can be hidden or controlled by the researcher.

Disadvantages of using action research design

1. It is difficult to perform conventional studies because it is the responsibility of the
researcher to boost change for study.
2. Over-involvement of the researcher may bias the test results.
3. There is no standard format to write action research, therefore, it is hard to
document.
4. Because of its cyclic nature action research is difficult and time consuming to
conduct.

3) Cohort Research design

A cohort study is generally conducted on a certain population (have some commonality or
similarity) over a period of time. A cohort study is usually applied in medical sciences and
social sciences. A cohort study makes note of statistical occurrence with a specialized
subsection of the population, which is unified by similar characteristics that are relevant
with the problem being investigated, instead of studying statistical occurrence with the
general population.A cohort can either be open or closed but not both at the same time.
Cohort studies collect data applying the method of observation using a qualitative
framework. Open cohort studies involve dynamic population which is separated by the state
of being studied in the problem.

The size of a cohort study is not constant because the date of entry and exit is defined by an
individual. Rate-based data is gathered in open cohort studies. Closed cohort study involves
a specific population, where all the participants enter the study at a specific point and no
new participants are allowed to take part in later.

Therefore, the number of participants in a closed cohort study remain constant and in a few
rare cases, it can only decrease.
Advantages of using Action research study
1. In risk-based studies, using action research study is mandatory, because it is
unethical to involve random people.
2. Both original and secondary data can be used in cohort research.
3. A cohort study is flexible in its nature and can be used to provide insights into effects
over time and different types of changes for example, social, political, economic, and
cultural.
 18

4. Cohort studies can gauge probable cause before the outcome has occurred. It can
establish that these causes led to the result. Therefore, avoid the debate determining
which is the cause and which is the effect.

Disadvantages of cohort research design

1. Because of lack of randomization, the external legitimacy of a cohort study is lower
than the other researches which select random participants.
2. Cohort studies usually take a long time because the researcher has to wait for certain
conditions within the group. Therefore, there are chances that variables may change
with time, hence, impacting the credibility of the results.
3. In the case of comparison of two cohort groups, the factors which differ between the
two groups can’t be controlled.

4) Causal design :
This type of research study is used to analyze the phenomena of conditional statements like
“if A, then B”. the purpose of using this type of research is to evaluate the impact of a
specific change on the existing standards and conventions.
In most of the social studies, a causal explanation is required to test the hypothesis.
Causality can be determined by observing the variation in the variables which are assumed
to be causing a change in the other variables.
Causal research is difficult to perform and there is never a certainty that there is no other
factor influencing the results, especially when the research is dealing with people’s
emotions and attitudes. But there could be other deeper psychological reasons that even the
subject is not conscious of.
There are a total of three conditions to determine the causality.

a. Empirical association: An effective deduction is based on finding a correlation

between the independent variable and dependent variable
b. Appropriate time order: The independent variable must be tackled before the
dependent variables.
c. Nonspuriousness: A relationship between two variables which is independent of
variation is called a third variable.

Advantages of using a causal research study

1. There are high chances of replication in this type of research design.
2. This study has internal validity because of systematic subject selection.
 19

3. By proving a causal link between variables and eliminating other possibilities, it

helps people to understand the world better.

Disadvantages of using causal research study

1. All relationships can’t be causal. There are chances that two unrelated events seem to
be related.
2. It is difficult to determine the conclusions about causal relationships, because of
various superfluous and perplexing variables that exist in a social environment.
Hence, causality can only be inferred, never proven.
3. The cause must come before the effect if two variables are related to each other. It is
difficult to tell which variable is the cause and which variable is effect in a causal
design.

5) Descriptive design :
This type of research design is used to describe the characteristics of a population or
phenomena being researched. This study provides the answer to “what” and does not
provide the answers to “how”, “when”, and “why”. Descriptive research does not require an
internal validity to describe the characteristics of a population. This type of research is used
to calculate frequencies, averages, and statistic of data.

Advantages of using Descriptive research design

1. This approach gathers a large amount of data for the study.
2. With the help of this study rich data can be yielded for future references.
3. A more focused study can be developed by using the limitations of the study as a
useful tool.
4. The descriptive design gives a general overview of the study which is helpful to
determine useful pointers for which variables are worth studying.

Disadvantages of using Descriptive research design

This study entirely depends on the instrumentation for observation and measurement.
1. The outcome of a descriptive design can’t be used to disprove a hypothesis.
2. Outcomes of descriptive designs can’t be replicated as outcomes of this design is
collected using the observational method

6) Cross-sectional design :
 20

This type of research design can only calculate among or from a variety of people,
phenomena or subjects at the place of change. It has three distinguishing features such as no
time dimensions, a dependence on the existing differences, and selection of groups based
on differences rather than random selection.

Advantages of using a cross-sectional design

1. Cross-sectional research design
2. is inexpensive to perform because this is done using surveys.
3. Results are more reliable because it is performed on a population.
4. This study provides the characteristics of the result at a point in time.
5. Grouping of the population is done based on their difference and are not selected
randomly.
6. A cross-sectional study can use a large number of subjects, unlike many other
research designs.

Disadvantages of using cross-sectional study

1. It is difficult to find people, phenomena or subjects of the same interest.
2. Outcomes are time-bound and do not provide any reliability for historical
occurrences.
3. This study can’t be used to determine the cause and effect relationship.
4. AS outcomes are time bound, therefore, there are chances of getting different
outcomes in different time-frames.

7) Exploratory design :
This type of research design is used for the research on which no research has been done
before and has no studies to refer to. The focus of exploratory design is to get
understanding and knowledge for later investigations. This study determines if a future
study is possible or not and later techniques can be developed for more research.
Advantages of using Exploratory research design

1. It helps to determine research priority.

2. It is useful to gather background data for a particular topic.
3. This research answers all questions like “what”, “why”, “how”

Disadvantages of using exploratory design

1. Findings of the exploratory group are not generalized on the whole population.
 21

2. Outcomes of this study are tentative, because of its unstructured style of research.

8) Experimental design

This type of research design is often used when there is a priority of time such as cause will
always precede effect and when there is steadiness in a causal relationship such as a
particular cause will always lead to the same effect and the degree of association is great.

Experimental design is the blueprint of the procedure that permits researchers to control all
factors of the experiment. Experimental designs use more groups and more measurements
for a longer period of time.

Advantages of using experimental design

1. It delivers a high level of evidence for a single study.
2. This study determines what is the cause of something to take place.
3. It helps researchers to determine placebo effects from treatment effects.

Disadvantages of using experimental research design

1. Experimental research is not real and it might not fit into the real world.
2. The settings of the experiment may change the behavior of the subjects.
3. The experimental research is sometimes costly, because of the use of special
equipment and facilities.
4. There are a few types of problems which can’t be experimented with because of
ethical or technical reasons.

9) Longitudinal design :
Longitudinal research design makes repetitive experiments and makes multiple
observations. In this type of research design, the same group of people is interviewed at
regular intervals. In this way, the researcher tracks their behavior and identifies variables
that have caused the change in their behaviors. This research study is a type of
observational study and is also known as a panel study.

Advantages of using longitudinal research study

1. Observation can be made during a particular phenomenon.
2. Future outcomes can be predicted on the basis of earlier factors.
3. Let the research establish a causal relationship between various variables.
4. Provide an explanation for the pattern of change.
 22

Disadvantages of using Longitudinal Research Study

1. Methods of conducting experiments might change over time.
2. Original sample might change over time.
3. More than one variable can’t be shown in this type of research.
4. In this type of research, the researcher assumes that the present trends will remain the
same in future also.
5. It takes a long time to conduct this type of research.

10) Historical design

In this type of research data from the past is collected, evaluated and the hypothesis is
defended based on the outcomes. To do this type of research a lot of resources like logs,
documents, notes, diaries, reports, official records, archives, and no textual data like maps,
images, drawings, audios) are used. This research is difficult to conduct because documents
should be authentic and authorized.

Advantages of Historical research design

1. It is useful for trend analysis.
2. It can provide a contextual background to understand a research problem better.
3. There are no chances of emotional involvement of the researcher with the subject.
4. Historical resources can be used multiple times.

Disadvantages of Historical Research design

1. The success of research completely relies on the quality of historical resources.
2. External variables can’t be controlled in this type of research; thus, research remains
weak.
3. Gaps in the study are difficult to acknowledge because of the missing pieces of
historical resources.
4. Interpretation of historical resources consumes a lot of time.

11) Observational research design :

This type of research design is used to draw results by comparing subjects under research
with a controlled group. An observational study can be of two types. In the first type, your
subjects know that you are observing them and in the second type, you observe your
subjects without letting them know. Observational research design lets you get the insights
of a particular phenomenon without getting into the trouble of setting up a large project.
 23

Advantages of observational research design

1. It is a flexible type of research and doesn’t require you to stick to a hypothesis.
2. In-depth information can be collected about the phenomenon.
3. Results can be generalized to real life events.
4. It can act as a pre-research before starting any other experiment.
5. It accounts for the complexity of group behavior.

Disadvantages of observational research design

1. Subjects under study are not equally credible.
2. There are high chances for this research turned out to be biased because the
researcher might notice what he wants to notice.
3. The outcome of this research is limited to a small group and can’t be generalized.
4. Subjects might behave differently because of the presence of the researcher.

12) Sequential research design :

This type of research is designed in a staged approach, where you can move to the next
stage only after completing research at the first stage. The results from one stage are used in
the next stage and this process continues until enough data is collected to test the
hypothesis.
The sample size can vary throughout the research. After analyzing each stage, research can
admit the null hypothesis or can choose a different hypothesis or even can choose to
perform the experiment again. That means in this type of research design there is no limit
on a number of subjects selected by a researcher.

Advantages of using sequential research design

1. There is no limit on the size of the sample of research.
2. Repetitive nature of the research lets you make initial changes.
3. A sequential research design is not expensive.
4. Fewer efforts from the researcher’s side.
5. Because of its sequential nature, results of one sample are analyzed and tested before
taking the second sample into the study.

Disadvantages of using Sequential Research design

1. It is difficult to maintain consistency in the research from one sample to another.
 24

2. Samples aren’t randomized. Hence outcomes can’t be generalized to the whole

population.
3. Moving the results of one sample to another is difficult work.

OR
Explanatory Research

Explanatory Research is usually held for those that were researched not so well, or demands
priorities, generates operational definitions and provides a better-researched model. It is one
of the various types of research that is focused on details.
A person who investigates begins with the general, main idea and starts using research as a
tool that provides a better understanding of the subject that is going to be investigated in the
future. That is why the aim is simple: having a small amount of information gives you more
and more to succeed in it finally. To start research, you need to make an outline or speech
outline to pitch your research idea to your professor or a boss or in a board meeting.

What is Explanatory Research

Explanatory research is very easy to understand – it is research which is making for
discovering a problem that hasn’t ever been studied clearly, to make definitions and
explanations that haven't been made before and improve final results. Usually, this type of
research relies on several important techniques:
● secondary research – such as looking for newly available literature.
● informal qualitative approaches, such as talking with other people, competitors or
consumers.
● formal qualitative research through in-depth interviews, focus groups, projective
methods, case studies or pilot studies

Purpose of Explanatory Research

As everyone knows, there are a lot of reasons why research is done. But do you know what
the purposes are? Why do you need to take into account all the styles, techniques and
experiments made before?Why did we develop an entire group of sciences to understand
humans? Because what good is being human if you cannot explain why we do something.
Maybe I am a little too ‘meta’ about all this. The purpose of psychology is to explore, to
describe and to explain how and why a person thinks, feels and acts.

Purpose of Explanatory Research:

 25

Increasing Understanding: a very strong aim is to increase understanding between

common people, or other researchers among the topics that are investigated. It is not a
summary or something like that – it is just an explanation of what and why something is
investigating and happening.

The flexibility of Sources: in the explanatory type of research it is very common to use
literature or data that have been already published. Think a lot before giving the list of
sources – it has to be informative and concrete, and moreover precise.

Better Conclusions: Explanation research can be very useful with having the aim to
continue research approaches. A good understanding and explanation of the subject allows
the researcher to post further research questions that will make great progress in the sphere
he investigates. Also, this type of work is very good for a scientist to understand better his
aim.
Some of the popular methods of explanatory research design include:

1. Focus Groups:
It is a method of the advanced level; here you have to gather from 8 up to 12 people who
have to know at least some information about it. In the best variant, they will know as much
as you do, it will increase the level of results very much.

2. Depth Interview:
But the very good start is, to begin with, one speech with one well-educated person who
knows a lot about your topic. It can be anyone – professional or specialist from your work,
and so on, no matter who, but matters his level of competency. Depth interviews are used
widely for getting information and experience from people with some information
connected with the concrete topic which you are discovering. Really, anyone with the
information you need is a good candidate for this interview.

3. Case Analysis:
Researchers can understand and solve the problem more effectively by researching similar
cases or other groups who had a similar case. This analysis will help to understand the
situation better, and to avoid the appearance of problems again.

4. Literature Search:
 26

One of the easiest and the fastest ways is a search for literature. Also, this is one of the
cheapest ways to get needed information, hypothesis. Just look around, there is so much
information available on the Internet and in libraries.
This search can include journals, newspapers, scientific literature and lots more. By the way
the Internet is still the best way to get needed information without even going out of the
house.Believe that this article is useful and you found what you have been looking for here.

Descriptive Research
Descriptive research is a type of research that describes a population, situation, or
phenomenon that is being studied. It focuses on answering the how, what, when, and where
questions of a research problem, rather than the why.
This is mainly because it is important to have a proper understanding of what a research
problem is about before investigating why it exists in the first place.
For example, an investor considering an investment in the ever-changing Amsterdam
housing market needs to understand what the current state of the market is, how it changes
(increasing or decreasing), and when it changes (time of the year) before asking for the
why. This is where descriptive research comes in.

What Are The Types of Descriptive Research?

Descriptive research is classified into different types according to the kind of approach that
is used in conducting descriptive research. The different types of descriptive research are
highlighted below:
● Descriptive-survey
Descriptive survey research uses surveys to gather data about varying subjects. This data
aims to know the extent to which different conditions can be obtained among these
subjects.
For example, a researcher wants to determine the qualification of employed professionals in
Maryland. He uses a survey as his research instrument, and each item on the survey related
to qualifications is subjected to a Yes/No answer.
This way, the researcher can describe the qualifications possessed by the employed
demographics of this community.

● Descriptive-normative survey
This is an extension of the descriptive survey, with the addition being the normative
element. In the descriptive-normative survey, the results of the study should be compared
with the norm.
 27

For example, an organization that wishes to test the skills of its employees by a team may
have them take a skills test. The skills tests are the evaluation tool in this case, and the
result of this test is compared with the norm of each role.If the score of the team is one
standard deviation above the mean, it is very satisfactory, if within the mean, satisfactory,
and one standard deviation below the mean is unsatisfactory.

● Descriptive-status
This is a quantitative description technique that seeks to answer questions about real-life
situations. For example, a researcher researching the income of the employees in a
company, and the relationship with their performance.
A survey will be carried out to gather enough data about the income of the employees, then
their performance will be evaluated and compared to their income. This will help determine
whether a higher income means better performance and low income means lower
performance or vice versa.

● Descriptive-analysis
The descriptive-analysis method of research describes a subject by further analyzing it,
which in this case involves dividing it into 2 parts. For example, the HR personnel of a
company that wishes to analyze the job role of each employee of the company may divide
the employees into the people that work at the Headquarters in the US and those that work
from the Oslo, Norway office.
A questionnaire is devised to analyze the job role of employees with similar salaries and
who work in similar positions.

● Descriptive classification
This method is employed in biological sciences for the classification of plants and animals.
A researcher who wishes to classify the sea animals into different species will collect
samples from various search stations, then classify them accordingly.

● Descriptive-comparative
In descriptive-comparative research, the researcher considers 2 variables that are not
manipulated, and establishes a formal procedure to conclude that one is better than the
other. For example, an examination body wants to determine the better method of
conducting tests between paper-based and computer-based tests.
 28

A random sample of potential participants of the test may be asked to use the 2 different
methods, and factors like failure rates, time factors, and others will be evaluated to arrive at
the best method.

● Correlative Survey
Correlative surveys are used to determine whether the relationship between 2 variables is
positive, negative, or neutral. That is, if 2 variables, say X and Y are directly proportional,
inversely proportional or are not related to each other.
Examples of Descriptive Research
There are different examples of descriptive research that may be highlighted from its types,
uses, and applications. However, we will be restricting ourselves to only 3 distinct
examples in this article.

● Comparing Student Performance:

An academic institution may wish 2 compare the performance of its junior high school
students in English language and Mathematics. This may be used to classify students based
on 2 major groups, with one group going ahead to study while courses, while the other
study courses in the Arts & Humanities field.
Students who are more proficient in mathematics will be encouraged to go into STEM and
vice versa. Institutions may also use this data to identify student's weak points and work on
ways to assist them.

● Scientific Classification
During major scientific classification of plants, animals, and periodic table elements, the
characteristics and components of each subject are evaluated and used to determine how
they are classified.
For example, living things may be classified into kingdom Plantae or kingdom animal
depending on their nature. Further classification may group animals into mammals, pieces,
vertebrae, invertebrae, etc.
All these classifications are made a result of descriptive research which describes what they
are.
● Human Behavior
When studying human behaviour based on a factor or event, the researcher observes the
characteristics, behaviour, and reaction, then use if to conclude. A company willing to sell
to its target market needs to first study the behaviour of the market.
 29

This may be done by observing how its target reacts to a competitor's product, then use it to
determine their behaviour.
What are the Characteristics of Descriptive Research?
The characteristics of descriptive research can be highlighted from its definition,
applications, data collection methods, and examples. Some characteristics of descriptive
research are:
● Quantitativeness
Descriptive research uses a quantitative research method by collecting quantifiable
information to be used for statistical analysis of the population sample. This is very
common when dealing with research in the physical sciences.
● Qualitativeness
It can also be carried out using the qualitative research method, to properly describe the
research problem. This is because descriptive research is more explanatory than exploratory
or experimental.
● Uncontrolled variables
In descriptive research, researchers cannot control the variables like they do in experimental
research.
● The basis for further research
The results of descriptive research can be further analyzed and used in other research
methods. It can also inform the next line of research, including the research method that
should be used.
This is because it provides basic information about the research problem, which may give
birth to other questions like why a particular thing is the way it is.

Conclusive Research (add much more the resources are low)

The conclusive research supplies the manager information useful to assess different
alternative courses of action and select the most appropriate from them. The conclusive
research furnishes a rational basis for a manager’s decisions. The alternatives may be well
defined or vague. Formal research procedures are the major characteristics of conclusive
research. The research objectives and the information needs are exactly explained.
Descriptive or experimental are the two categories of conclusive research.

Experimental Research
What is Experimental Research?
 30

Experimental research is a study that strictly adheres to a scientific research design. It

includes a hypothesis, a variable that can be manipulated by the researcher, and variables
that can be measured, calculated and compared. Most importantly, experimental research is
completed in a controlled environment. The researcher collects data and results will either
support or reject the hypothesis. This method of research is referred to as hypothesis testing
or a deductive research method (Babbie 4).
What is the Purpose of Experimental Research?
Experimental research seeks to determine a relationship between two (2) variables—the
dependent variable and the independent variable. After completing an experimental
research study, a correlation between a specific aspect of an entity and the variable being
studied is either supported or rejected.
What type of Data are Collected in Experimental Research?
Data in experimental research must be able to be quantified, or measured. Data collected
could be acidity/alkalinity, area, circumference, density, electrical
current/potential/resistance, force, growth (time, weight, volume, length/width), heat,
humidity, light intensity, mass, pressure, sound intensity, temperature, time, velocity,
volume or weight. However, the entity should be carefully observed qualitatively, or
described using
words and photographs. How does the entity look, smell, sound, feel, and taste (when
appropriate)? These types of observations help supplement the measurements taken
throughout the experiment.
Sampling and Sampling Design

A sample design is a definite plan for obtaining a sample from a given population. It refers
to the technique or the procedure the researcher would adopt in selecting items for the
sample. Sample design may as well lay down the number of items to be included in the
sample i.e., the size of the sample. Sample design is determined before data are collected.
There are many sample designs from which a researcher can choose. Some designs are
relatively more precise and easier to apply than others. Researcher must select/prepare a
sample design which should be reliable and appropriate for his research study.

STEPS IN SAMPLE DESIGN

While developing a sampling design, the researcher must pay attention to the following
points:
 31

1. Type of universe: The first step in developing any sample design is to clearly define
the set of objects, technically called the Universe, to be studied. The universe can be
finite or infinite. In finite universe the number of items is certain, but in case of an
infinite universe the number of items is infinite.
2. Sampling unit: A decision has to be taken concerning a sampling unit before
selecting sample. Sampling unit may be a geographical one such as state, district,
village, etc., or a construction unit such as house, flat, etc., or it may be a social unit
such as family, club, school, etc., or it may be an individual.
3. Source list: It is also known as ‘sampling frame’ from which sample is to be drawn.
It contains the names of all items of a universe (in case of finite universe only). If
source list is not available, researcher has to prepare it. Such a list should be
comprehensive, correct, reliable and appropriate.
4. Size of sample: This refers to the number of items to be selected from the universe
to constitute a sample. This a major problem before a researcher. The size of sample
should neither be excessively large, nor too small. It should be optimum. The size of
population variance needs to be considered as in case of larger variance usually a
bigger sample is needed. The size of population must be kept in view for this also
limits the sample size.
5. Parameters of interest: In determining the sample design, one must consider the
question of the specific population parameters which are of interest.There may also
be important subgroups in the population about whom we would like to make
estimates. All this has a strong impact upon the sample design we would accept.
6. Budgetary constraint: Cost considerations, from practical point of view, have a
major impact upon decisions relating to not only the size of the sample but also to
the type of sample. This fact can even lead to the use of a non-probability sample.
7. Sampling procedure: Finally, the researcher must decide the type of sample he will
use i.e., he must decide about the technique to be used in selecting the items for the
sample. In fact, this technique or procedure stands for the sample design itself.

CRITERIA OF SELECTING A SAMPLING PROCEDURE

1.Inappropriate sampling frame: If the sampling frame is inappropriate i.e., a biased

representation of the universe, it will result in a systematic bias.
2. Defective measuring device: If the measuring device is constantly in error, it will result
in systematic bias. In survey work, systematic bias can result if the questionnaire or the
 32

interviewer is biased. Similarly, if the physical measuring device is defective there will be
systematic bias in the data collected through such a measuring device.
3. Non-respondents: If we are unable to sample all the individuals initially included in the
sample, there may arise a systematic bias. The reason is that in such a situation the
likelihood of establishing contact or receiving a response from an individual is often
correlated with the measure of what is to be estimated
4. Indeterminacy principle: Sometimes we find that individuals act differently when kept
under observation than what they do when kept in non-observed situations.
5. Natural bias in the reporting of data: Natural bias of respondents in the reporting of
data is often the cause of a systematic bias in many inquiries. There is usually a downward
bias in the income data collected by the government taxation department, whereas we find
an upward bias in the income data collected by some social organisation.

DIFFERENT TYPES OF SAMPLE DESIGNS

There are different types of sample designs based on two factors viz., the representation
basis and the element selection technique. On the representation basis, the sample may be
probability sampling or it may be non-probability sampling. Probability sampling is based
on the concept of random selection, whereas non-probability sampling is ‘non-random’
sampling, On element selection basis, the sample may be either unrestricted or restricted.
Thus, sample designs are basically of two types viz., non-probability sampling and
probability sampling. We take up these two designs separately.

Non-probability sampling: Non-

probability sampling is that sampling
procedure which does not afford any
basis for estimating the probability
that each item in the population has
been included in the sample. Non-
probability sampling is also known by
different names such as deliberate
sampling, purposive sampling and judgement sampling. In this type of sampling, items for
the sample are selected deliberately by the researcher; his choice concerning the items
remains supreme. In other words, under non-probability sampling the organisers of the
inquiry purposely choose the particular units of the universe for constituting a sample on
 33

the basis that the small mass that they so select out of a huge one will be typical or
representative of the whole.

Probability sampling
Probability sampling is also known as ‘random sampling’ or ‘chance sampling’. Under this
sampling design, every item of the universe has an equal chance of inclusion in the sample.
It is, so to say, a lottery method in which individual units are picked up from the whole
group not deliberately but by some mechanical process. Here it is blind chance alone that
determines whether one item or the other is selected. The results obtained from probability
or random sampling can be assured in terms of probability i.e., we can measure the errors of
estimation or the significance of results obtained from a random sample, and this fact brings
out the superiority of random sampling design over the deliberate sampling design. Random
sampling ensures the law of Statistical Regularity which states that if on an average the
sample chosen is a random one, the sample will have the same composition and
characteristics as the universe. This is the reason why random sampling is considered as the
best technique of selecting a representative sample.

UNIT 3: METHODS AND TECHNIQUES OF DATA COLLECTION

The task of data collection begins after a research problem has been defined and research
design/ plan chalked out. While deciding about the method of data collection to be used for
the study, the researcher should keep in mind two types of data viz., primary and secondary.
The primary data are those which are collected afresh and for the first time, and thus
happen to be original in character. The secondary data, on the other hand, are those which
have already been collected by someone else and which have already been passed through
the statistical process. The researcher would have to decide which sort of data he would be
using (thus collecting) for his study and accordingly he will have to select one or the other
method of data collection. The methods of collecting primary and secondary data differ
since primary data are to be originally collected, while in case of secondary data the nature
of data collection work is merely that of compilation.
A variety of methods and techniques are available for collecting the specific information
required for a study. The researcher needs to be cognizant of the resources available for
the study and the level of accuracy required. The sources of data could either be primary
or secondary in nature
 34

1. Primary data
The primary data generated the first time, is problem or project specific and is gathered
with the specific purposes. The genuineness and the pertinence is logically high. The
resource implications of and the monetary involvement are quite high. At occasions a
researcher might not possess the resources or the time or both to proceed with primary data.
In such cases the researcher may search for other thrifty and genuine options data so that
the study may be carried further.

2. Secondary data
The information which is not topic or research specific and is gathered and documented by
some other researcher or research agency is known as secondary data. This information is
maintained and given publicly in a format with an explicitly defined structure, is accessible
soon and managed. Compared to the original research specific data, secondary data can be
thrifty and collected in less time. Also the information collected is contextual. The primary
and original data for one researcher may be secondary and historical for some other
researcher.

Procedure for Primary Data Collection

The primary data collection procedure
involves a number of steps:

1. Planning the study

2. Modes of data collection
3. Sample Selection
4. Editing the primary data
 35

1. Planning the Study: As the extent of quality of conclusion obtained from statistical
data depends upon the attribute of collected information, it is of great significance
that a standard investigation process is established to assure that the data is
representative and unbiased. This needs a high level of skill and also certain
precautionary measures may have to be adopted.
2. Modes of Primary data collection: Three commonly utilized methods for gathering
of primary data are:
- Observation of subjects
- Experimentation
- Administration of Questionnaire
Observation
The researcher or the persons hired by him collect the information by observing the work
process. For example, the researcher may go to a service station, pose as a customer and
observe. What is the best location in supermarket in the shelf? This method eliminates the
response bias. The observation can be applied to investigate techniques of selling,
movements and responses of customers etc. But the customer’s/ consumers’ mental state,
motives for buying decisions, their product images are not laid open to view. The
information regarding their income and education is not evident. It is also time-taking for
the researcher to wait for specific sections to occur.

Experimentation
Many of the important decisions facing the marketing executive cannot be resolved by
secondary research by observing or by surveying the attitudes of customers or experts.
Experimental methods may be used in many circumstances like opting the best method for
training and remuneration plan for salesmen, the appropriate shelf arrangement for
displaying a product, determining the effectiveness of a point-of-purchase display, the most
effective media. In a marketing experiment the experimental units may be consumers,
stores, sales territories, etc. Variables, which the researcher can control, which can be
studied are price, packaging, display, sales incentive plan, flavor, color, shape etc. The
results of a marketing experiment will be in the form of sales, attitudes or behavior.

Survey and Questionnaire

Surveys and questionnaires are 2 similar tools used in collecting primary data. They are a
group of questions typed or written down and sent to the sample of study to give responses.
 36

After giving the required responses, the survey is given back to the researcher to record. It
is advisable to conduct a pilot study where the questionnaires are filled by experts and
meant to assess the weakness of the questions or techniques used.
There are 2 main types of surveys used for data collection, namely; online and offline
surveys. Online surveys are carried out using internet-enabled devices like mobile phones,
PCs, Tablets, etc. They can be shared with respondents through email, websites, or social
media. Offline surveys, on the other hand, do not require an internet connection for them to
be carried out.

3. Sample selection: Sample selection is a very important but sometimes

underestimated part of a research study. Sampling theory describes two sampling
domains: probability and nonprobability. Probability samples contain some type of
randomization and consist of simple, stratified, systematic, cluster, and sequential
types.
4. Editing the primary data: Data editing is defined as the process involving the
review and adjustment of collected survey data. ... The purpose is to control the
quality of the collected data. Data editing can be performed manually, with the
assistance of a computer or a combination of both. While editing primary data, the
following points should be considered :-
- Editing for consistency
- Editing for completeness
- Editing for accuracy
- Editing for uniformity or homogeneity

Limitations of Primary Data Collection

The primary data collection suffers from a number of limitations.
1. This primary data collection needs great skills in the interviewer as the respondents
may not be willing to furnish information. Therefore, the interviewer has to assure
respondents that the information will remain confidential.
2. The lack of knowledge, memory or inability to find out their motives may be the
possible reasons for the inability of the respondents to provide information.
3. There are also semantic difficulties due to which respondents are unable to provide
exact information. It is often difficult to articulate a question in such a manner that it
communicates accurately the same sense to all respondents. Similarly two different
words of a single question may often produce different results.
 37

However, these limitations can be managed to a limited extent by cautious phrasing of

questions, deploying specially trained investigators and careful interpretation by a clear
recognition of the limitations of the data and an understanding of what exactly the data
represent.

Development and designing tool of data collection

Different types of studies may be conducted through the collection of primary data. Some
important types of studies are discussed below:

Structured Study
Structured Study If a car manufacturer wanted to know how many people own a car, what
is the make of it, when they purchased the car, the respondents would be asked a number of
questions in a particular sequence.

Do you have a car? Yes/No (if yes )

What is the make of it? Make __________
When did you purchase it? Date _____________
This constitutes an example of structured and non disguised study

Non-Structured Study
The marketing personnel want to understand the reasons people buy or refuse to buy their
products more than anything else.Reasons for their buying a product can be categorized as:
❖ Reasons for an individual's own purposes or attitudes.
❖ Reasons for outside influences such as advertising
❖ Those reasons based on characteristics of product itself
This approach is still far from being satisfactory. Many will not report base or socially
unacceptable motives. To overpower these difficulties, psychoanalysts have developed
several techniques
 38

Projective Technique
In project technique a respondent is asked to explain an ambiguous situation posed to him.
A projection shows the personality and attitudes of the respondents in the situation
described. Several projective techniques are used, but word-association, sentence-
completion and storytelling are widely used techniques. In word-companionship a series of
words is told one at a time to the respondent. After each word, the respondent states the
thing that emerges in his mind. The sentence-completion needs the respondent to complete
a portion of the sentence. In story telling the respondent visualizes a picture or reads a
description and asks to tell a story about it.

Measurement Scales
There are four different scales of measurement used in research; nominal, ordinal, interval
and ratio. The rules used to assign numeral objects define the kind of scale and level of
measurement. A brief account of each scaling type is given below;

1. Nominal Scales: Nominal scale is the simplest form of measurement. A variable

measured on a nominal is one which is divided into two or more categories, for
example, gender is categorized as male or female, a question as to whether a family
owns a iPhone can be answered ‘Yes’ or ‘No’. It is simply a sorting operation in
which all individuals or units or answers can be placed in one category or another
(i.e. the categories are exhaustive). The essential characteristic of a nominal scale is
that in terms of a given variable, one individual is different from another and the
categories are discriminated against (i.e. the categories are mutually exclusive). This
characteristic of classification is fundamental to all scales of measurement. Nominal
scales that consist of only two categories such as female-male, agree-disagree,aware-
unaware, yes-no, are unique and are called dichotomous scales. Such dichotomous
nominal scales are important to researchers because the numerical labels for the two
scale categories can be treated as though they are of interval scale value.

2. Ordinal Scales: Ordinal scales have all the properties of a nominal scale, but, in
addition, categories can be ordered along a continuum, in terms of a given criterion.
Given three categories A, B and C, on an ordinal scale, one might be able to say, for
e.g., that A is greater than B and B is greater than C. If numerals are assigned to
ordinal scale categories, the numerals serve only as ranks for ordering observations
from least to most in terms of the characteristic measured and they do not indicate
 39

the distance between scale that organizes observations in terms of categories such as
high, medium and low or strongly agree, agree, not sure, disagree, and strong
disagree.

3. Interval Scales: Interval scales incorporate all the properties of nominal and ordinal
scales and in addition, indicate the distance or interval between the categories. In
formal terms one can say not only that A is greater than B and B is greater than C but
also that (A-B)=(B-C) or (A-C)=(A-B)+(B-C). Examples of interval scale include
age, income and investments. However, an interval scale is one where there is no
absolute zero point. It can be placed anywhere along a continuum e.g., the age can be
between 20 to 60 years and need not necessarily start from 0 years. This makes a
ratio comparison, that A is twice that of B or so wrong.

4. Ratio Scales: A special form of interval scale is the ratio scale which differs in that
it has a true zero point or a point at which the characteristic that is measured is
presumed to be absent. Examples of ratio scales include, weight, length, income,
expenditure and others. In each there is a concept of zero income, zero weight, etc.
Since ratio scales represent a refinement of interval scales, generally these scales are
not distinguished and both the terms are used interchangeably.
Measurement of attitudes
Validity and Reliability of the tools of data collection.

1. Validity

Validity relates to the degree to which a test measures

what one actually desires to measure. A widely
accepted classification of validity consists of content,
criterion-related, construct.

A. Content Validity

Content validity refers to the space to which a

measure adequately covers the topic under study. It is
the representativeness or adequacy in sampling of the content of a measuring
instrument. If the instrument contains a sample which is representative of the population
of the subject matter of interest, content validity is satisfactory. In order to assess the
 40

content validity of an instrument, one must first consent on the elements constituting
adequate inclusion of the problem.

B. Criterion related validity

Criterion-related validity indicates the success of measures used for predicting or

estimation. The researcher may desire to predict an outcome or estimate the existence of
a current behavior or condition. The first is predictive and second is concurrent validity,
respectively. They differ only in a time perspective. Criterion-related validity is
examined by making a comparison of test or scale scores with one or more external
variables, or criteria believed to measure the attribute under study.

C. Construct validity

The concept of content validity is one of the most significant developments in modern
measurement theory and practice. It is a significant advancement as it combines
psychometric notions with theoretical concepts. The measurement expert seeks to
explain individual differences in the test scores of a measuring instrument.

D. Predictive validity

The predictive validity involves the ability of a phenomena measured at one point of
time to predict another phenomenon in future. If the correlation coefficient between the
two is high, the measure has a high predictive ability.

2. Reliability

Reliability is related to consistency, accuracy and

predictability of the measure. It indicates the extent to
which a process of measurement is devoid of random
errors. Two methods may be used for checking the
reliability of a scale: Test-retest reliability and split-
half reliability

1.Test-retest reliability

In this method, measurements repeated of the same respondents using the same
measure under similar conditions are taken. A scale is reliable when the two score are
highly correlated.

2. Split-half reliability
 41

Split-half method is applied in case of multiple item measure. The number of items is
divided on a random basis into two equal parts and a correlation coefficient between the
two is computed. A high correlation indicates that the internal consistency of the
construct takes to greater reliability.

UNIT IV:
FIELDWORK IN RESEARCH AND DATA PROCESSING
After the data has been collected it needs processing and analyzing in accordance with
an outline chalked down while formulating the research plan. This is essential to ensure
that all relevant data is attained for comparisons and analysis envisaged for the study.
Thus, editing, coding, classification and tabulation of data to make them capable of
analysis comprises the processing of data. The computation of particular measures
and the search for relationships among groups of data is known as data analysis.
Thus, associations or differences accepting or rejecting the initial or new hypotheses
should be statistically tested to determine the validity with which data can be stated to
indicate any conclusions. But certain scholars do not make any difference between
processing and analysis. They think that a number of closely related operations carried
out for summarizing and organizing that the research questions find their answers

1. Data Editing

Once the validation process has been accomplished, the next step is the editing of the
raw data obtained. A process of examining the raw data for the study (particularly in
surveys) to find out errors and omissions and to rectify them where possible, is known
as data editing. The data is exact in terms of information recorded and responses tried to
obtain. Further, the obtained responses are in the decided format, filled consistently,
complete in all respects and arranged in proper sequence to make it easier for coding
and tabulation.

To ensure that data screening and cleaning which is essentially the requirement of the
editing process, has been carried out, the researcher needs to carry out the process at two
levels, at the field editing and central editing:
 42

a. Field-editing
In field editing the researcher examines the reporting form filled by
the investigator for entirely finalizing all such forms which are
written in abbreviation at the time of recording the responses.
Sometimes a person’s writing cannot be easily read, this kind of
editing becomes necessary. The field editing needs to be carried out
soon after the interview. When the Editing Central Editing Field
Editing investigator finds that some questions remain unanswered
while doing field editing, the investigator must resist from
imagining what the respondent would have said if he had been asked the question. In
quality research there is no room for self-interviewing.

b. Central Editing
Central editing takes place at the time all forms lacking nothing have been received in the
office. Central editing is carried out by a single editor in case of a small study and a team of
editors for a large inquiry carry out a thorough editing. Editor(s) may rectify the evident
errors such as an entry in the wrong space and time.

(a) Backtracking
The best and most efficient way of handling unsatisfactory responses is to return to the
field, and go back to the respondents. This technique is best used for industrial surveys,
where it is easier to track the respondent, who can be persuaded to give Central Editing
Discarding Unsatisfactory responses Backtracking Allocating missing values Plug value
 43

answers to the non-response or illegible answers. In individual surveys, this becomes a little
difficult as the persons locality and contact details might not be availa

(b) Allocating missing values

This is a contingency plan that the researcher might need to adopt in case going back to the
field is not possible. Then the option might be to assign a missing value to the blanks or the
unsatisfactory responses. However, this works in case: The number of blank or wrong
answers is small The number of such responses per person is small The important
parameters being studied do not have too many blanks; otherwise the sample size for those
variables becomes too small for generalizations.
(c) Plug value
When the variable under study is the key variable, then sometimes the researcher might
insert a plug value. Sometimes one can plug an average or a neutral value in such cases, for
example a 3 for a five-point scale. Sometimes a decision rule based upon probability could
be established and the researcher might decide on a thumb rule (for example, for a yes/no
question, he might decide to put ‘yes’ the first time he encounters missing value or no at the
second and so on. Another way to handle this situation is to conduct an exploratory data
analysis and see what the ratio of yes to no answers is and accordingly establish the
decision rule
(d) Discarding unsatisfactory responses

If the response sheet has too many blanks/illegible or multiple responses for a single
answer, the form is not worth correcting and editing. Hence, it is much better to completely
discard the whole questionnaire. If too many forms are discarded then the sample for the
study might become too small for an analysis or generalization, so here it is advisable to
carry out another round of field visits

Classification and Tabulation & interpretation of Data

1. Classification:

Classification aims to reduce voluminous raw data into identical groups to derive
meaningful relationships on the basis of general characteristics. Data with a general
characteristic are arranged in categories in one class and thus whole data get arranged into
different groups or classes. Based on the nature of the phenomenon involved, classification
can be one of the two types.
 44

1. Attribute Classification
Descriptive (such as literacy, sex, honesty, etc.) and numerical (such as weight, height,
income, etc.) are the two general characteristics to classify data. Descriptive characteristics
mean qualitative phenomena where it is not possible to quantify variables, the researcher
simply can notice their presence or absence in a specific item. Data received on definite
characteristics are known as statistics of attributes and their classification.

2. Class interval Classification

The numerical characteristics denote that quantitative phenomenon is quantitatively
measured in statistical units. Data pertaining to income, production, age, weight, etc. are
categorized based on class intervals.s. The frequency of the class is the number of items
occurring in a given class. The entire classes with their respective frequencies in the form
of a table are known as group frequency distribution

INTERPRETATION OF DATA

Once the data has been cleaned and entered in a tabular form, the researcher is advised to
do a preliminary data exploration in order to assess the expected trends of the findings.
Sometimes, these indicative trends may demonstrate that the data collection or instrument
design is faulty and needs some corrections. Thus, before one goes about testing the
formulated hypotheses, one carries out a loosely structure exploration. Most of the
exploration is done on the basis of the graphical and visual display of the data patterns that
seem to be emerging. The following are some widely used and simplistic measures of
displaying data.
 45

1. Bar and pie charts

The data that is available as classification or demographic variable is most often on a
categorical or nominal scale. Thus, the tabled data can be plotted to demonstrate the pattern
of responses. For example, in a study on jeweler buying the age groups of the sample group
and the occupations were as follows:

2. Histogram
For metric-interval and ratio scale data, the data is represented through a histogram. The
representation would be able to demonstrate the distribution pattern in terms of whether it is
normally distributed or demonstrates skewness.

3. Stem and leaf displays

This is another way of displaying the metric data. It is very easy to compute and can be
done manually or with the help of Minitab. It shows individual data values in each set as
against the histogram which presents only group aggregates. It shows the pattern of
responses in each interval and yet can maintain the rank order for a quick approximation of
the median or quartile. Each row or line is called a stem and each value on the line is a leaf.
The same data that we represented on the histogram can also be depicted on a stem and leaf
display.
Testing of Hypothesis
The major research objective of inferential statistics is testing of research hypotheses
through statistical hypotheses. The hypothesis is tested based on the information obtained
from a sample. Business uses the hypothesis tests widely and industry uses them for
decision-making. There are two types of hypotheses: Null hypothesis and alternative
hypothesis. Similarly, there are two tests: one tailed test and two-tailed tests.

Statistical Significance
 46

Following the sampling approach, a hypothesis is accepted or rejected on the basis of

sampling information alog. Since any sample will almost vary somewhat from its
population, it must be judged whether these differences are statistically significant.

In tests of significance, two kinds of hypotheses are used.

● The null hypothesis is used for testing.
● Null hypothesis is a statement that no difference exists between the parameter and
the statistic being compared to it.
● The researchers usually test to determine whether a real difference exists. The
hypothesis for testing is not stated in a positive form. This type of hypothesis cannot
be tested definitively.
●
One tailed and two-tailed tests

● A test is called one-tailed only if the null hypothesis gets rejected when the value of
the test statistic falls in acceptance region of the distribution.
● A test is regarded as one-tailed if the null hypothesis is rejected at the time the value
of the test statistic occurs in the region of acceptance of the distribution.
● The test is two-tailed if the null hypothesis gets rejected when the value of the test
statistic occurs in either of the two tails of its sampling distribution.
● The test is considered as two-tailed if the null hypothesis is rejected at the time the
value of the test statistic occurs in the either of the two tails of the sampling
distribution
For Example
The company would like to test the hypothesis if the average content of the containers
varies from 300 ml.
A one tailed test can be expressed as H0 : µ = 300 ml
H1 : µ ≠ 300 ml

We can call these hypotheses as two tailed hypothesis

The problem of overfilling of containers could be written as:
H = µ = 300 ml
H1 = µ > 300 ml
 47

These hypotheses are known as one tailed hypothesis. Here the analyst would be concerned
in the upper tail of the sampling distribution. However, if the issue is under-filling of the
containers, the hypotheses may be stated as:
H0 = µ = 300 ml
H1 = µ < 300 m
is of the distribution

Type I and type II error

The acceptance and rejection of a hypothesis depends upon the similar results. There is ever
a chance of the sample not representing the population and therefore, resulting in errors and
the results drawn could be faulty

If null hypothesis is true and is accepted or when the null hypothesis is false is rejected,
in either case the decision is right.
\However, if the hypothesis is actually true, but is rejected, Type I error is committed.
The committing of Type I error is indicated with alpha (α). Similarly, if the null
hypothesis is accepted, when actually it is false the researcher commits type II error. The
chances of committing a Type II error are indicated by beta (β).
1-β is called the power of test.
 48

Procedure of Testing of Hypothesis

1. Setting up of a hypothesis
The first step in hypothesis testing is to get a hypothesis about a population parameter.
State the null hypothesis, H0, and the alternative hypothesis, Ha . The set up alternative
hypothesis represents what the researcher is trying to prove. The null hypothesis represents
the negation of what the researcher is trying to prove.

2. Level of Significance
The function of hypothesis testing is compelled to choose a significance level. The level of
significance (α) is chosen prior to sample selection.
The significance level indicates the anticipation of rejection of the null hypothesis at the
time it is really correct. The value varies from issue to issue but often it is adopted as either
5 per cent or 1 percent. A five per cent level of significance is interpreted that there would
be 5 chances out of one hundred that a null hypothesis is rejected while it is to be accepted.

3. Decision on a test statistics

Various test statistics include t, Z, X2 or F, depending upon different assumptions.

4, Determination of a critical region

It is crucial to clearly state the values of test statistics resulting in rejection or acceptance of
the null hypothesis. The critical region causes the null hypothesis to be rejected. With a
given level of significance, α is the optimal critical region for a two-tailed test containing
 49

α/2 per cent area in the right tail of the distribution plus α/2 percent in the left tail of the
distribution if the null hypothesis is rejected. Therefore, establishing a critical region is
similar to determining a 100 (1-α) percent confidence interval.

5 Computing the value of test-statistics

The value of the test statistic is dependent upon the random sample of size n. Once the
computation of the value of test statistic is carried out, we must verify if the sample results
take place in the region of criticality or the acceptance region.

6. Decision-Making
There may be two alternatives. The hypothesis either is rejected or is accepted based upon
the occurrence of the value of the test statistic in the rejection region or the region of
acceptance. The management decision relies upon the statistical decision for rejecting null
hypothesis or accepting the null hypothesis
If the analyst tests the hypothesis at a 5 percent level of significance, it would be
rejected if the observed results have a probability less than 5 per cent.

7 Standard Error and Sampling Distribution

The standard deviation of the sampling distribution is called the standard error. It measures
the sampling variability due to chance or random forces.

8.Test Statistic for Testing Hypothesis

 50

An overview of Parametric and Non-parametric tests

Parametric Tests
The basic principle behind the parametric tests is that we have a fixed set of parameters that
are used to determine a probabilistic model that may be used in Machine Learning as well.
Parametric tests are those tests for which we have prior knowledge of the population
distribution (i.e, normal), or if not then we can easily approximate it to a normal
distribution which is possible with the help of the Central Limit Theorem.
Parameters for using the normal distribution is –
● Mean
● Standard Deviation

Eventually, the classification of a test to be parametric is completely dependent on the

population assumptions. There are many parametric tests available from which some of
them are as follows:
● To find the confidence interval for the population means with the help of known
standard deviation.
● To determine the confidence interval for population means along with the unknown
standard deviation.
● To find the confidence interval for the population variance.
● To find the confidence interval for the difference of two means, with an unknown
value of standard deviation.

Non-parametric Tests
In Non-Parametric tests, we don’t make any assumption about the parameters for the given
population or the population we are studying. In fact, these tests don’t depend on the
population.
Hence, there is no fixed set of parameters available, and also there is no distribution
(normal distribution, etc.) of any kind is available for use. This is also the reason that
nonparametric tests are also referred to as distribution-free tests. In modern days,
Non-parametric tests are gaining popularity and an impact of influence some reasons
behind this fame is –
● The main reason is that there is no need to be mannered while using parametric tests.
● The second reason is that we do not require to make assumptions about the
population given (or taken) on which we are doing the analysis.
 51

● Most of the nonparametric tests available are very easy to apply and to understand
also i.e. the complexity is very low.

A) Parametric Tests for Hypothesis testing

● T-test
● Z-test
● F-test
● ANOVA

B) Non-parametric Tests for Hypothesis testing

● Chi-square

T-Test
1. It is a parametric test of hypothesis testing based on Student’s T distribution.
2. It is essentially testing the significance of the difference of the mean values when the
sample size is small (i.e, less than 30) and when the population standard deviation is
not available.
3. Assumptions of this test:
● Population distribution is normal, and
● Samples are random and independent
● The sample size is small.
 52

● Population standard deviation is not known.

● Mann-Whitney ‘U’ test is a non-parametric counterpart of the T-test.

A T-test can be a:
One Sample T-test: To compare a sample mean with that of the population mean.

Where,
x̄ is the sample mean
s is the sample standard deviation
n is the sample size
μ is the population mean

Two-Sample T-test: To compare the means of two different samples.

where,
x̄1 is the sample mean of the first group
x̄2 is the sample mean of the second group
S1 is the sample-1 standard deviation
S2 is the sample-2 standard deviation
n is the sample size
Conclusion:

● If the value of the test statistic is greater than the table value -> Rejects the null
hypothesis.
● If the value of the test statistic is less than the table value -> Do not reject the null
hypothesis.
Z-Test
 53

1. It is a parametric test of hypothesis testing.

2. It is used to determine whether the means are different when the population variance
is known and the sample size is large (i.e, greater than 30).
3. Assumptions of this test:
● Population distribution is normal
● Samples are random and independent.
● The sample size is large.
● Population standard deviation is known.
A Z-test can be:
One Sample Z-test: To compare a sample mean with that of the population mean.

Two Sample Z-test: To compare the means of two different samples.

where,
x̄1 is the sample mean of 1st group
x̄2 is the sample mean of 2nd group
σ1 is the population-1 standard deviation
σ2 is the population-2 standard deviation
n is the sample size
 54

F-Test
1. It is a parametric test of hypothesis testing based on Snedecor F-distribution.
2. It is a test for the null hypothesis that two normal populations have the same
variance.
3. An F-test is regarded as a comparison of equality of sample variances.
4. F-statistic is simply a ratio of two variances.
5. It is calculated as:
F = s12/s22

6. By changing the variance in the ratio, F-test has become a very flexible test. It can
then be used to:
● Test the overall significance for a regression model.
● To compare the fits of different models and
● To test the equality of means.

7. Assumptions of this test:

● Population distribution is normal, and
● Samples are drawn randomly and independently.

ANOVA
1. Also called as Analysis of variance, it is a parametric test of hypothesis testing.
2. It is an extension of the T-Test and Z-test.
3. It is used to test the significance of the differences in the mean values among more
than two sample groups.
4. It uses F-test to statistically test the equality of means and the relative variance
between them.
5. Assumptions of this test:
● Population distribution is normal, and
● Samples are random and independent.
● Homogeneity of sample variance.
6. One-way ANOVA and Two-way ANOVA are types.
7. F-statistic = variance between the sample means/variance within the sample
 55

Chi-Square Test
1. It is a non-parametric test of hypothesis testing.
2. As a non-parametric test, chi-square can be used:
● test of goodness of fit.
● as a test of independence of two variables.
3. It helps in assessing the goodness of fit between a set of observed and those expected
theoretically.
4. It makes a comparison between the expected frequencies and the observed
frequencies.
5. Greater the difference, the greater is the value of chi-square.
6. If there is no difference between the expected and observed frequencies, then the
value of chi-square is equal to zero.
7. It is also known as the “Goodness of fit test” which determines whether a particular
distribution fits the observed data or not.
8. It is calculated as:

9. Chi-square is also used to test the independence of two variables.

10. Conditions for chi-square test:
● Randomly collect and record the Observations.
● In the sample, all the entities must be independent.
● No one of the groups should contain very few items, say less than 10.
● The reasonably large overall number of items. Normally, it should be at least 50,
however small the number of groups may be.
11. Chi-square as a parametric test is used as a test for population variance based on
sample variance.
12. If we take each one of a collection of sample variances, divide them by the known
population variance and multiply these quotients by (n-1), where n means the
number of items in the sample, we get the values of chi-square.
13. It is calculated as:
 56

Essential ideas of Multivariate analysis of data

Multivariate analysis may be defined as a collection of methods for analysis of data in
which a several independent number of observations represent a dependent variable
available to define such a relationship. The techniques that take account of the various
relationships among variables are termed multivariate analysis.

Objectives of Multivariate Analysis :

- To transform large number of observations into smaller composite scores
- To predict the variability of the dependent variable based on its covariance with all
the independent variables.
- To classify individuals or objects into one of the two or more mutually exclusive and
exhausting groups on the basis of a set of independent variables

Advantages and Disadvantages of Multivariate Analysis

- The main advantage of multivariate analysis is that since it considers more than one
factor of independent variables which influence the variability of dependent
variables, the conclusion drawn is more accurate.
- The conclusion are more realistic and nearer to the real life situation.\
- The main disadvantages of multivariate analysis include that it requires rather
complex computations to arrive at a satisfactory conclusion.
- A large number of observations for large number of variables need to be collected
and tabulated it is a rather time consuming process.
57
 58

An overview of dependence and interdependence methods:

 59

Statistical Packages - SPSS.

SPSS is short for Statistical Package for the Social Sciences, and it’s used by various kinds
of researchers for complex statistical data analysis. The SPSS software package was created
for the management and statistical analysis of social science data.
SPSS is used by market researchers, health researchers, survey companies, government
entities, education researchers, marketing organizations, data miners, and many more for
processing and analyzing survey data, such as you collect with an online survey platform
like Alchemer.
Most top research agencies use SPSS to analyze survey data and mine text data so that they
can get the most out of their research and survey projects.
The Core Functions of SPSS
1. Statistics Program
SPSS’s Statistics program provides a plethora of basic statistical functions, some of
which include frequencies, cross-tabulation, and bivariate statistics.
2. Modeler Program
SPSS’s Modeler program enables researchers to build and validate predictive models
using advanced statistical procedures.
3. Text Analytics for Surveys Program
SPSS’s Text Analytics for Surveys program helps survey administrators uncover
powerful insights from responses to open-ended survey questions.
4. Visualization Designer
SPSS’s Visualization Designer program allows researchers to use their data to create
a wide variety of visuals like density charts and radial boxplots from their survey
data with ease.
In addition to the four programs mentioned above, SPSS also provides solutions for data
management, which allow researchers to perform case selection, create derived data, and
perform file reshaping.
 60

UNIT V: REPORTING IN RESEARCH

Report
Reporting is an important communication skill both in spoken and written communication.
The word ‘report’ comes from the Latin word, ‘Reportare’ which means ‘to carry back’. To
report means to give information about something seen, observed, done, or heard. Likewise
a report is a statement of something seen, observed, done, or heard. Accordingly the report
writing skill involves:
1. Writing an account of something for presentation to others or for publication;
2. Giving a formal statement or official account of the results of an investigation;
3. Presenting something referred for study, action, etc. with the conclusions reached or
recommendations made; and
4. Preserving formal or official facts or the record of some proceedings or an investigation.

A report is a systematic and well-organised document which defines and analyses a definite
issue or a problem. It presents information in an organized format for specific addressees
and purposes. While summaries of reports may be delivered orally, complete reports are
almost always in the form of written documents.

The preparation and presentation of the research report is the conclusive stage in the
process of research. If the results of the research are not expressed in a concise form and
transmitted to the marketing management in an understandable and meaningful form, the
efforts devoted to the research serves no purpose. If the report is creating confusion or
written in an appropriate manner, all the resources spent on collection and analysis of data
would not yield any result.

Types of Research Reports

The research report may be either technical or popular in its orientation. The same
procedure is followed in both the approaches in description of the research, its
methodology, findings, conclusions and recommendations. The research report may differ
in their style of writing, use of key terms and length. Often higher levels of the executive,
the shorter the report will be.

1.Brief reports
These reports are usually brief and do not possess any formal structure. Often they do not
exceed four to five pages. Such reports provide limited scope of information. They are
prepared either for instant use or as a preliminary to the formally structured report to
 61

follow. Working papers or basic reports and survey reports

could be the frameworks for these reports. These reports are
important as a reference point at the time of writing the
final report or the researcher desires to revisit the detailed
steps undertaken in collecting the information related to the
study. Survey reports might or might not have an academic
relevance. The concentration is on the present findings
simple to understand including figures and tables. Then the
patterns in findings are studied to infer appropriate
conclusions.

2.Detailed reports
The detailed reports aim at a more common audience who is not well informed with the
minute details of research methodology and other terms. The presentation of the detailed
reports is a little more live with more focus on headlines, flow diagrams, charts, tables and
summaries for the purpose of highlighting major points. In addition, various kinds of
audiences show interest in the results of the same marketing research study. Detailed
reports are written in the form of both a technical report and a popular report.

3.Technical reports
Other researchers usually make use of technical reports. These reports enable other
researchers to be an evaluator of methodology, calculations and identify accuracy and the
steps followed.

4.Business reports
Business report would not have technical strictness and details of the technical report. The
language of the report would be as the manager understands. The conclusions of the study
must enable the manager in decision-making. The report must be supplemented with tables
and figures. The pictorial presentation is done with the help of bar diagrams and graphs.
The reporting tone would be more in business terms.

Format of Report,
● The reporting and spreading widely the study and its findings needs a structured
format and by and large, the process is standardized.
 62

● The key difference amongst the kinds of reports is that all the components that
essentially form a research report would be available only in a detailed technical
report.
● The review of literature would be performed merely as a routine in the management
report; however,
● they would be detailed and go along with the bibliography in the technical report.
● Usage of theoretical and technical jargon would be more in the technical report and
visual presentation of data would be greater in the management report.
● The process of report formulation and presentation is shown in Fig.1. The title, letter
of transmittal, letter of authorization, table of contents, executive summary and
acknowledgements are included in the preliminary section.
● The next section presents the background section detailing the problem statement,
study introduction and background, scope and objectives of the study as well as the
review of literature.
● The methodology section is specific to the technical report.
● The methodology section includes research design, sampling design, data collection
and data analysis.
● This is followed by a findings section constituting the results and interpretation of
results.
● Then appear the conclusions section incorporating conclusions, recommendations
and the limitations of the study.
● The technical report would have a detailed bibliography at the end.
● In the management report, the sequencing of the report might be reversed to suit the
needs of the decision-maker, as the reader needs to review and absorb the findings.
● The findings of the study ought to be furnished in such a manner that they can be
applied directly as inputs for making decisions.
● Thus, the final section would be presented immediately after the study objectives and
a short reporting on methodology could be presented in the appendix.
● Thus, the entire research report needs to be recorded either as a single written report
or into several reports, depending on the needs of the readers.
● The researcher would need to assist the business manager in deciphering the report,
executing the findings, and in case of need, to revise the report to suit the specific
actionable requirements of the manager.

Format of Report
Structure and Example of a Research Report
 63

● Title
This is the title of your systematic investigation. Your title should be concise and point
to the aims, objectives, and findings of a research report.
● Table of Contents
This is like a compass that makes it easier for readers to navigate the research report.
● Abstract
An abstract is an overview that highlights all important aspects of the research including
the research method, data collection process, and research findings. Think of an abstract as
a summary of your research report that presents pertinent information in a concise manner.
An abstract is always brief; typically 100-150 words and goes straight to the point. The
focus of your research abstract should be the 5Ws and 1H format – What, Where, Why,
When, Who and How.
● Introduction
Here, the researcher highlights the aims and objectives of the systematic investigation
as well as the problem which the systematic investigation sets out to solve. When writing
the report introduction, it is also essential to indicate whether the purposes of the research
were achieved or would require more work.
In the introduction section, the researcher specifies the research problem and also outlines
the significance of the systematic investigation. Also, the researcher is expected to outline
any jargons and terminologies that are contained in the research.
● Literature Review
A literature review is a written survey of existing knowledge in the field of study. In
other words, it is the section where you provide an overview and analysis of different
research works that are relevant to your systematic investigation.
It highlights existing research knowledge and areas needing further investigation, which
your research has sought to fill. At this stage, you can also hint at your research hypothesis
and its possible implications for the existing body of knowledge in your field of study.
● An Account of Investigation
This is a detailed account of the research process, including the methodology, sample,
and research subjects. Here, you are expected to provide in-depth information on the
research process including the data collection and analysis procedures.
In a quantitative research report, you'd need to provide information surveys, questionnaires
and other quantitative data collection methods used in your research. In a qualitative
research report, you are expected to describe the qualitative data collection methods used in
your research including interviews and focus groups.
 64

● Findings
In this section, you are expected to present the results of the systematic investigation.
● Discussion
This section further explains the findings of the research, earlier outlined. Here, you are
expected to present a justification for each outcome and show whether the results are in line
with your hypotheses or if other research studies have come up with similar results.
● Conclusions
This is a summary of all the information in the report. It also outlines the significance of
the entire study.
● References and Appendices
This section contains a list of all the primary and secondary research sources.

Report Preparation and Presentation of Reports

Irrespective of the kind of report, the reporting and spreading widely the study and its
findings needs a structured format and by and large, the process is standardized. The key
difference amongst the kinds of reports is that all the components that essentially form a
research report would be available only in a detailed technical report. The review of
literature would be performed merely as a routine in the management report; however, they
would be detailed and go along with the bibliography in the technical report. Usage of
theoretical and technical jargon would be more in the technical report and visual
presentation of data would be greater in the management report.
The process of report formulation and presentation is shown in Fig.1.
 65

1. Primary Function - The title, letter of transmittal, letter of authorization, table of

contents, executive summary and acknowledgements are included in the preliminary
section
2. Background- The next section presents the background section detailing problem
statements, study introduction and background, scope and objectives of the study as
well as the review of literature.
3. Methodology- The methodology section is specific to the technical report. The
methodology section includes research design, sampling design, data collection and
data analysis
4. Findings- This is followed by the findings section constituting the results and
interpretation of results.
5. Conclusion- Then appear the conclusions section incorporating conclusions,
recommendations and the limitations of the study
6. Bibliography- The technical report would have a detailed bibliography at the end
Thus, the entire research report needs to be recorded either as a single written report or into
several report, depending on the need of the readers. The researcher would need to assist
the business manager in deciphering the report, executing the findings, and in case of need,
to revise the report to suit the specific actionable requirements of the manager.
66