MANIPAL UNIVERSITY JAIPUR

ASSIGNMENT SUBMISSION
NAME - RANJITHA.M
ROLL NO - 2314516088

PROGRAM - MASTER OF BUSINESS ADMINISTRATION (MBA)

SEMESTER - III
COURSE CODE & NAME - DMBA301 RESEARCH METHODOLOGY

NUMBER OF ASSIGNMENTS - ASSIGNMENT 1 & ASSIGNMENT 2

ANSWER 1 –

The Meaning of Research

Research refers to a systematic process of inquiry that involves gathering, analyzing, and
interpreting information or data to increase understanding, answer questions, or solve
problems. It is a structured approach to investigating a specific topic, issue, or hypothesis,
and it follows established methods to ensure reliability, validity, and credibility. Research
plays a crucial role in advancing knowledge across various fields such as science, social
sciences, humanities, and business.
The primary goal of research is to contribute to existing knowledge by either confirming
previous findings or generating new insights. Researchers employ various techniques and
methodologies to collect data, interpret results, and draw conclusions. These findings can
be used to inform practice, shape policy, or spark further inquiry.
Types of Research
Research can be categorized in several ways depending on the approach, purpose, and
methodology. Below are the main types of research:
1. Basic (Fundamental) Research
Basic research is driven by curiosity and aims to expand knowledge without any
immediate practical application in mind. It focuses on understanding underlying
principles, theories, and concepts. For example, studying the genetic structure of
organisms may not have immediate real-world applications, but it lays the
foundation for future developments in fields like medicine or agriculture.
 2. Applied Research
In contrast to basic research, applied research is practical and aims to solve specific,
real-world problems. It involves the application of theories or principles to address
challenges in areas such as technology, healthcare, education, or business. An
example of applied research is studying the effectiveness of a new drug to treat a
particular disease.
3. Descriptive Research
Descriptive research seeks to describe characteristics or phenomena as they exist in
a particular setting. It involves collecting data to provide a detailed account of
situations, events, or behaviors. For example, a study surveying customer
satisfaction with a product would collect descriptive data without necessarily
analyzing the underlying causes of satisfaction.
4. Exploratory Research
Exploratory research is conducted when a researcher has limited knowledge about a
topic and seeks to gain more insights. It helps identify patterns, ideas, or concepts
that can be further studied in more detail. This type of research is common in new or
emerging fields where not much is known.
5. Explanatory (Causal) Research
Explanatory research focuses on understanding cause-and-effect relationships.
Researchers aim to determine how one variable influences another. For instance, a
study that investigates the impact of social media usage on mental health is
explanatory, as it seeks to explain the cause of mental health changes due to social
media exposure.
6. Quantitative Research
Quantitative research involves the collection and analysis of numerical data to
identify patterns, relationships, or trends. It uses statistical tools to test hypotheses
or measure variables. For example, conducting a survey to quantify consumer
preferences for a product involves quantitative methods.
7. Qualitative Research
Qualitative research focuses on understanding human behavior, experiences, and
social phenomena in a more in-depth, non-numerical manner. It uses methods like
interviews, focus groups, and case studies to gather rich, detailed data. Qualitative
research often explores the "how" and "why" behind patterns or behaviors.
Conclusion
Research, in its various forms, is fundamental to advancing knowledge and solving practical
problems. Whether seeking to understand basic principles or addressing real-world
challenges, the different types of research provide valuable insights that contribute to the
development of knowledge in every domain.
ANSWER 2 –

Types of Data and Primary Data Collection Methods

Data is essential in research and can be categorized into various types, each serving
different analytical needs. The main types of data are qualitative and quantitative, with
further subdivisions that help define the nature of the information being collected.
1. Qualitative Data: This type of data is descriptive and non-numeric, used to capture
qualities or characteristics. It is often categorized into:
o Nominal Data: Represents categories without a specific order (e.g., colors,
gender, types of products).
o Ordinal Data: Involves categories with a meaningful order, but the
differences between them are not consistent (e.g., satisfaction levels,
education levels).
2. Quantitative Data: This data is numeric and measurable, used to quantify variables.
It can be divided into:
o Discrete Data: Data that takes distinct, countable values (e.g., number of
children, number of employees).
o Continuous Data: Data that can take any value within a given range, often
measured (e.g., height, weight, temperature).
3. Interval Data: Numeric data with consistent intervals between values but no true
zero point (e.g., temperature in Celsius or Fahrenheit).
4. Ratio Data: The highest level of measurement, with consistent intervals and a
meaningful zero point (e.g., income, age, distance).
Methods of Primary Data Collection
Primary data refers to information gathered directly from original sources, specifically for
the research at hand. There are several methods to collect primary data, each suitable for
different research needs:
1. Surveys and Questionnaires: Surveys are widely used for collecting data from large
groups. They can include closed-ended questions (e.g., multiple choice, yes/no) or
open-ended questions that allow respondents to elaborate. Surveys are cost-
effective and efficient but may suffer from low response rates or biased answers.
2. Interviews: Interviews involve direct interaction with respondents. They can be
structured (with predefined questions), semi-structured (allowing some flexibility),
or unstructured (open-ended and conversational). Interviews provide in-depth
insights but are time-consuming and may be influenced by interviewer bias.
 3. Focus Groups: A small group of participants discusses a topic guided by a moderator.
Focus groups provide rich qualitative data and encourage interaction among
participants, which can spark new ideas. However, they may be subject to
groupthink, and the sample may not be representative.
4. Observation: Observational research involves watching and recording behaviors or
events without interference. It can be participant (researcher actively involved) or
non-participant (researcher is an outsider). This method offers real-world insights
but can be affected by observer bias and ethical concerns.
5. Experiments: Experiments manipulate variables in controlled environments to
observe their effects. This method is particularly useful in establishing cause-and-
effect relationships. However, it may lack ecological validity and raise ethical issues,
especially in social research.
6. Case Studies: Detailed investigations of specific instances or cases provide deep
insights, especially in complex situations. However, findings from case studies may
not be generalizable to larger populations.
Each of these methods provides valuable insights depending on the research goals, and
combining multiple methods can enhance data reliability and depth.

ANSWER 3 –

Types of Questions in a Questionnaire and Their Need

In questionnaire design, the types of questions included play a crucial role in how well the
survey captures the intended data. Selecting the right question types is essential for
ensuring clarity, ease of response, and the accuracy of the information gathered. The main
types of questions in a questionnaire are broadly categorized into closed-ended questions,
open-ended questions, and scaled questions, each serving distinct purposes in data
collection.
1. Closed-Ended Questions
Closed-ended questions are those where the respondent is provided with predefined
answer options. These questions are easy to analyze as they produce quantifiable data.
• Yes/No Questions: These questions offer two response choices: "Yes" or "No". They
are simple, quick to answer, and ideal for capturing straightforward information. For
example, "Do you own a car?" This type is useful for binary decision-making.
• Multiple-Choice Questions: Respondents choose one or more options from a list of
predetermined choices. This format is useful for collecting specific data in a
structured format, such as "Which of the following products have you purchased in
 the last month? (Select all that apply)". It allows for comparisons and analysis of
preferences.
• Dichotomous Questions: These are similar to yes/no questions but can include other
two-choice options like "True/False" or "Agree/Disagree". They are simple, reducing
ambiguity, and easy to analyze.
Need for Closed-Ended Questions: Closed-ended questions help streamline the data
collection process, reduce variability in responses, and make the analysis more
straightforward. They are particularly useful in large-scale surveys where quantifiable data is
needed quickly and efficiently.
2. Open-Ended Questions
Open-ended questions allow respondents to answer in their own words, providing more
detailed and nuanced insights.
• Example: "What improvements would you suggest for our customer service?"
Need for Open-Ended Questions: These questions provide rich qualitative data and are
ideal for exploring respondents’ thoughts, feelings, or experiences in depth. They allow for
the discovery of unexpected insights and enable the researcher to understand the reasoning
behind certain behaviors or opinions. Open-ended questions are particularly useful in
exploratory research or when the researcher wants to capture personal opinions and ideas.
3. Scaled Questions
Scaled questions are designed to measure the intensity or degree of a respondent’s feelings
or attitudes toward a particular statement. These questions typically involve Likert scales,
semantic differential scales, or numerical rating scales.
• Likert Scale: Respondents indicate their level of agreement or disagreement with a
statement, such as "Strongly Agree, Agree, Neutral, Disagree, Strongly Disagree."
• Example: "I am satisfied with the service provided by our company" (with scale
options from 1 = Strongly Disagree to 5 = Strongly Agree).
• Semantic Differential Scale: Respondents are asked to rate a concept between two
bipolar adjectives (e.g., "unfriendly" vs. "friendly"). This scale measures attitudes on
a continuum.
Need for Scaled Questions: Scaled questions help capture the intensity or frequency of
opinions and behaviors. They are essential for measuring perceptions, attitudes, and
satisfaction levels, providing valuable data for statistical analysis. These types of questions
enable researchers to quantify abstract concepts like satisfaction, trust, or loyalty.
4. Ranking Questions
Ranking questions ask respondents to rank items in a specified order based on their
preferences or importance.
 • Example: "Rank the following features of our product from most important to least
important: Price, Quality, Durability, Customer Service."
Need for Ranking Questions: These questions are useful when the researcher needs to
understand the relative importance of different factors or preferences. Ranking helps
prioritize attributes or items according to the respondent's preferences, providing insight
into decision-making processes.
Conclusion
The variety of question types in a questionnaire—closed-ended, open-ended, scaled, and
ranking—addresses different research needs. Closed-ended questions offer efficient data
for quantitative analysis, while open-ended questions allow for detailed qualitative insights.
Scaled questions measure intensity and attitudes, and ranking questions help prioritize
elements. Together, these questions ensure comprehensive, balanced data collection, which
is crucial for making informed conclusions and decisions.

ANSWER 4 –

Editing in Research and Data Collection

Editing refers to the process of reviewing and refining data collected from surveys,
interviews, observations, or any other method of primary data collection. The main
objective of editing is to ensure the accuracy, consistency, completeness, and clarity of the
data before it is analyzed. Editing is an essential step in the research process, as it helps
identify and correct errors, inconsistencies, or ambiguities in the collected data, ensuring
that the final dataset is ready for analysis.
Editing can be done at various stages of the data collection process, from when the data is
first recorded to the final dataset that will be analyzed. The aim is to make the data usable
and reliable for drawing conclusions. Editing is often carried out by researchers, data coders,
or statisticians who are trained to detect issues with the data.

Types of Editing
There are several types of editing that researchers can perform, depending on the stage of
data collection and the nature of the data. These include:
1. Field Editing (Initial Editing)
• Description: Field editing is carried out immediately after the data is collected, often
in the field itself. This type of editing is done while the data collection is still fresh,
and the data collector is still available to clarify any issues.
 • Purpose: The primary goal of field editing is to ensure that the data is complete,
coherent, and that no major errors are present before the data is returned for
further processing.
• Tasks Involved:
o Checking for missing responses or incomplete answers.
o Ensuring that all questions are answered (especially for open-ended
questions).
o Identifying illegible or ambiguous responses.
o Correcting obvious mistakes like skipped questions, misinterpretations, or
incomplete forms.
• Example: If a survey respondent has left several questions unanswered, the field
editor can either ask the respondent to complete them or make a note for further
follow-up.
2. Office Editing (Secondary Editing)
• Description: Office editing occurs after the data has been returned from the field.
This editing is typically done in a controlled environment, such as a research office or
data processing center, where more in-depth checks are performed.
• Purpose: The aim is to refine the data further, ensuring it is fully consistent, correct,
and formatted appropriately for analysis.
• Tasks Involved:
o Checking for consistency across answers within a survey (e.g., if one answer
contradicts another).
o Verifying that the data conforms to expected response patterns or
predefined codes.
o Detecting outliers or extreme values that may suggest errors.
o Standardizing responses (e.g., ensuring consistent date formats, or using
uniform units for measurement).
• Example: If one respondent answers a question about age as “25” and another as
“25 years,” the office editor would standardize both responses as just “25.”
3. Consistency Editing
• Description: Consistency editing checks for logical coherence between answers given
by a respondent within a questionnaire. This type of editing is especially important
for ensuring that responses across different questions align with each other.
• Purpose: To identify any contradictions or illogical patterns in the data that might
indicate errors or misunderstandings.
 • Tasks Involved:
o Ensuring that responses match expected patterns (e.g., if a person says they
are employed full-time, but their income data is inconsistent with that claim).
o Identifying mismatches in demographic data, like age and education level
(e.g., a 70-year-old who claims to be in elementary school).
• Example: If a respondent indicates they are married but then answers a question
about family size indicating they are single, this would be flagged for follow-up.
4. Logical Editing
• Description: Logical editing checks that responses follow a logical sequence and
conform to the rules of the survey or study. It ensures that answers make sense
within the context of the question.
• Purpose: To detect and correct answers that might be logically inconsistent or don't
adhere to the intended question format.
• Tasks Involved:
o Ensuring that respondents provide answers within the expected range or
category (e.g., a respondent selects "No" when asked if they own a car but
then selects "Toyota" as the car brand).
o Ensuring appropriate skipping of questions (if a respondent selects "No" to a
question, the follow-up questions might need to be skipped).
• Example: If a respondent claims to have attended college but later states they have
no formal education, this would trigger a logical review.
5. Completion Editing
• Description: Completion editing is concerned with ensuring that all required fields or
sections of the data collection tool (e.g., survey, interview form) are filled out
properly.
• Purpose: To identify incomplete or missing responses and to either correct them or
note them for future action.
• Tasks Involved:
o Checking that all sections of the questionnaire are filled out.
o Identifying any "Don't Know" or "No Answer" responses and determining if
they are appropriate or if they need to be revisited.
o Verifying that all questions relevant to a respondent have been answered.
• Example: If a survey respondent skips a crucial question, such as "Are you currently
employed?", the editor would mark it for follow-up or clarification.
6. Coding Editing
• Description: This type of editing is done when data needs to be converted into a
numerical or categorical format (coding) for analysis.
• Purpose: To ensure that all open-ended responses or complex data are appropriately
coded and standardized for further analysis.
• Tasks Involved:
o Converting open-ended responses into predefined codes (e.g., categorizing
various reasons for a behavior into a numerical code).
o Ensuring that responses follow coding instructions and conform to the format
needed for statistical analysis.
• Example: In a survey about customer satisfaction, responses like “Excellent service,”
“Great,” and “Very happy” might be coded as “1” (for “excellent”), while “Good”
might be coded as “2”.
Conclusion
Editing is a critical process in data collection, ensuring that the collected data is accurate,
consistent, and ready for analysis. The various types of editing—field editing, office editing,
consistency editing, logical editing, completion editing, and coding editing—serve specific
purposes in identifying and correcting errors, improving the reliability of the dataset, and
ensuring that the data is ready for meaningful interpretation. Proper editing enhances the
overall quality of research and ensures that conclusions drawn from the data are valid and
trustworthy.

ANSWER 5 –

Research Proposals and Reports: Key Components in Research

Research proposals and research reports are fundamental documents in the research
process. A research proposal outlines the plan for a study, justifying the need for the
research, its objectives, methodology, and anticipated outcomes. It serves as a roadmap for
the research and is often used to seek approval, funding, or support. A research report, on
the other hand, is a formal presentation of the research findings, methods, and conclusions.
It is typically the final product of a research project and serves to communicate the results
to stakeholders or the broader academic community.
Both documents are critical in the research process as they ensure that the research is well-
planned, structured, and effectively communicated. Below is a discussion of the key
components of a research report, which is typically organized into several sections.
Components of a Research Report
A well-organized research report typically includes the following key components:
1. Title Page
• Description: The title page is the first page of the report and provides basic
information about the research. It should be concise yet descriptive enough to
convey the scope and focus of the study.
• Includes:
o Title of the research.
o Researcher's name.
o Institution or organization affiliation.
o Date of submission.
2. Abstract
• Description: The abstract is a brief summary (usually 150-250 words) of the entire
research report, including the problem, methodology, key findings, and conclusions.
• Purpose: To provide readers with a quick overview of the research without reading
the entire report. It should be clear, concise, and informative.
• Includes:
o Research question or problem.
o Methodology used.
o Key results or findings.
o Conclusion or implications.
3. Introduction
• Description: The introduction sets the stage for the research by outlining the
background, context, and significance of the study. It provides the rationale for the
research and highlights the problem or research question being addressed.
• Purpose: To introduce the research topic, explain why the study is important, and
establish the context for the research.
• Includes:
o Background information on the research topic.
o Statement of the research problem or hypothesis.
o Objectives of the study.
o Importance and relevance of the research.
 o Overview of the structure of the report.
4. Literature Review
• Description: The literature review surveys existing research related to the topic and
presents the theoretical framework or concepts that inform the study. It critically
evaluates the strengths, weaknesses, and gaps in previous research.
• Purpose: To provide a foundation for the research by showing how the current study
fits into the broader academic discourse.
• Includes:
o Review of relevant theories, models, and frameworks.
o Summary of key studies, findings, and methodologies used in previous
research.
o Identification of research gaps or areas where further investigation is needed.
5. Research Methodology
• Description: This section explains how the research was conducted, detailing the
research design, methods, and techniques used to gather and analyze data. It
justifies the choice of methods and how they align with the research objectives.
• Purpose: To provide transparency and allow others to replicate the study if needed.
It also ensures that the methods used are appropriate for addressing the research
question.
• Includes:
o Research design (qualitative, quantitative, or mixed-methods).
o Sampling methods and selection criteria.
o Data collection techniques (e.g., surveys, interviews, experiments).
o Instruments or tools used (e.g., questionnaires, software).
o Data analysis methods (e.g., statistical techniques, thematic analysis).
6. Results
• Description: The results section presents the findings of the study in a clear and
objective manner, often using tables, figures, charts, and graphs to summarize the
data.
• Purpose: To provide a factual, straightforward presentation of the data collected,
without interpretation or analysis.
• Includes:
o Descriptive statistics (e.g., mean, median, standard deviation).
 o Graphs, charts, and tables to visualize data.
o Presentation of qualitative findings, if applicable.
o Statistical test results (e.g., p-values, correlation coefficients).
7. Discussion
• Description: The discussion section interprets the results, explaining their
implications and how they address the research question or hypothesis. This is
where the researcher compares findings with existing literature and explores their
significance.
• Purpose: To analyze the findings in relation to the research objectives and the
broader academic context.
• Includes:
o Interpretation of the results.
o Comparison with previous studies and theoretical frameworks.
o Implications of the findings for practice, policy, or further research.
o Limitations of the study (e.g., sample size, potential biases).
o Suggestions for future research.
8. Conclusion
• Description: The conclusion summarizes the key findings, their significance, and the
overall contributions of the research. It often emphasizes the practical applications
or theoretical implications of the research.
• Purpose: To provide a concise summary of the research and its key messages.
• Includes:
o Recap of the main research question or problem.
o Summary of key findings.
o Implications for theory, practice, or policy.
o Recommendations for future research.
9. References/Bibliography
• Description: This section lists all the sources cited in the report, including books,
articles, websites, and other academic works.
• Purpose: To give credit to original sources and allow readers to find further
information.
• Includes:
 o Full citations of all sources referenced in the text, formatted according to a
specific citation style (e.g., APA, MLA, Chicago).
10. Appendices
• Description: The appendices include supplementary materials that are relevant but
not essential to the main body of the report. These might include raw data,
additional tables, or detailed descriptions of research instruments.
• Purpose: To provide additional, detailed information that supports the report but is
too lengthy or detailed for inclusion in the main sections.
• Includes:
o Raw data or supplementary tables.
o Copies of survey instruments, questionnaires, or interview guides.
o Detailed explanations of methodologies or statistical analyses.

Conclusion
A research report is a comprehensive document that outlines the entire research process,
from the initial problem formulation to the final conclusions and recommendations. Each
component serves a unique purpose in ensuring the clarity, validity, and reliability of the
research. Together, these components help researchers communicate their findings
effectively and contribute to the broader academic community. The structure and content
of the report should be tailored to the specific research context, but maintaining clear
organization and presenting a logical flow of ideas is essential for making the research
accessible and impactful.

ANSWER 6 –

Problem Statement:
We are given a contingency table summarizing the relationship between gender and
education level (High School, Bachelors, Masters, Ph.D). We need to test whether gender
and education level are independent or dependent. The hypothesis testing will be
performed at a 5% level of significance.
Here’s the given data:

High School Bachelors Masters Ph.D. Total

Female 60 54 46 41 201
Male 40 44 53 57 194
Total 100 98 99 98 395
We want to test if gender and education level are independent of each other.

Step 1: State the Hypotheses

• Null Hypothesis (H₀): Gender and education level are independent.
• Alternative Hypothesis (H₁): Gender and education level are dependent.

Step 2: Set the Significance Level

We are given that the test should be performed at a 5% significance level (α = 0.05).

Step 3: Compute the Expected Counts

To test for independence, we need to calculate the expected frequency for each cell in the
table, assuming that gender and education level are independent. The formula for the
expected frequency is:
Eij=(row total)×(column total)/grand total
Where:
• Eij is the expected count for cell (i,j)
• row total is the sum of observations for a particular row,
• column total is the sum of observations for a particular column,
• grand total is the overall total number of observations (395 in this case).
Let's calculate the expected counts for each cell:
For Female, High School:
EFemale, High School=(201)×(100)/395=20100/395≈50.88
For Female, Bachelors:
EFemale, Bachelors=(201)×(98)/395=19798/395≈50.07
For Female, Masters:
EFemale, Masters=(201)×(99)/395=19999/395≈50.63
For Female, Ph.D:
EFemale, Ph.D=(201)×(98)/395=19798/395≈50.07
For Male, High School:
EMale, High School=(194)×(100)/395=19400/395≈49.12
For Male, Bachelors:
EMale, Bachelors=(194)×(98)/395=19012/395≈48.13
For Male, Masters:
EMale, Masters=(194)×(99)/395=19206/395≈48.62
For Male, Ph.D:
EMale, Ph.D=(194)×(98)/395=19012/395≈48.13
Step 4: Calculate the Chi-Square Statistic
Now, we calculate the chi-square statistic using the formula:
χ2=∑(Oij−Eij)2/Eij
Where:
• Oij is the observed frequency,
• Eij is the expected frequency.
We calculate this for each cell:
For Female, High School:
(60−50.88)2=50.88(9.12)2=50.8883.1744≈1.634
For Female, Bachelors:
(54−50.07)2=50.07(3.93)2=50.0715.4449≈0.308
For Female, Masters:
(46−50.63)2=50.63(−4.63)2=50.6321.4269≈0.423
For Female, Ph.D:
(41−50.07)2=50.07(−9.07)2=50.0782.2449≈1.642
For Male, High School:
(40−49.12)2=49.12(−9.12)2=49.1283.1744≈1.693
For Male, Bachelors:
(44−48.13)2=48.13(−4.13)2=48.1317.0569≈0.354
For Male, Masters:
(53−48.62)2=48.62(4.38)2=48.6219.1844≈0.395
For Male, Ph.D:
(57−48.13)2=48.13(8.87)2=48.1378.7369≈1.637
Step 5: Sum the Chi-Square Values
Now, we sum all the individual chi-square values:
χ2=1.634+0.308+0.423+1.642+1.693+0.354+0.395+1.637=7.086

Step 6: Degrees of Freedom (df)

The degrees of freedom for a chi-square test of independence is given by the formula:
df=(r−1)×(c−1)
Where:
• r is the number of rows (2, for Female and Male),
• c is the number of columns (4, for High School, Bachelors, Masters, Ph.D).
Thus:
df=(2−1)×(4−1)=1×3=3

Step 7: Find the Critical Value

Using a chi-square distribution table, we find the critical value for df=3 at a significance level
of 0.05:
Χ2critical=7.815

Step 8: Make a Decision

• If the calculated chi-square value is greater than the critical value, we reject the null
hypothesis.
• If the calculated chi-square value is less than or equal to the critical value, we fail to
reject the null hypothesis.
Here:
χ2=7.086 and χ2critical=7.815
Since 7.086<7.8157, we fail to reject the null hypothesis.

Conclusion
At the 5% significance level, we fail to reject the null hypothesis that gender and education
level are independent. This suggests that there is no significant evidence to conclude that
gender and education level are dependent, meaning that gender does not appear to affect
the level of education attained.