Definitions and Symbols

• Parameter: A parameter is a summary description of a

Sample and Sampling fixed characteristic or measure of the target population. A
parameter denotes the true value which would be obtained
Design if a census was undertaken.
• Statistic: A statistic is a summary description of a
characteristic or measure of the sample. The sample
statistic is used as an estimate of the population parameter.

Dr. Anoop Kumar Gupta

MAIT
1 2

Sample or Census Sample or Census

► A population is any complete group of entities ►Information about population parameters may
that share some common set of characteristics be obtained by taking a census or a sample.
and comprises the universe for the purpose of ►A census involves investigation of all the
the marketing research problem. individual elements that make up a population.
► The objective of most marketing research The population parameters can be calculated
projects is to obtain information about the directly in a straightforward way after the
characteristics or parameters of a population. census is enumerated.
►A sample is a subset, or some part of a larger
population selected for participation in the
study.
3 4
 Sample or Census Sample versus Census
► Budget and time limits are obvious constraints
►Sample characteristics, called statistics, are then
favoring the use of a sample.
used to make inferences about the population
► A census is both costly and time consuming to
parameters. conduct.
►The inferences that link sample characteristics ► A census is unrealistic if the population is large, as it
and population parameters are estimation is for most consumer products.
procedures and tests of hypotheses. ► In the case of many industrial products, however, the
population is small, making a census feasible as well
as desirable.
► Small population sizes as well as high variance in the
characteristic to be measured favour a census.
5 6

Sample versus Census Sample versus Census

►If the cost of sampling errors is high then a ► Non‐sampling errors are found to be the major
census, which eliminates such errors, is contributor to total error, whereas random
desirable. sampling errors have been relatively small in
magnitude.
►If the cost of non‐sampling errors is high (e.g.
interviewers incorrectly questioning target ► In most cases, accuracy considerations would favor
respondents) a sample, where fewer resources a sample over a census.
would have been spent, would be favored. ► A sample may be preferred if the measurement
process results in the destruction or contamination
►A census can greatly increase non‐sampling
of the elements sampled. For example, product
error to the point that these errors exceed the usage tests result in the consumption of the
sampling errors of a sample. product.
7 8
Sample versus Census Sample versus Census
►Reasons for Taking a Census ►Sampling may also be necessary to focus
1. To eliminate the possibility that by chance a attention on individual cases, as in the case of
randomly selected sample may not be in‐depth interviews.
representative of the population. ►Finally, other considerations, such as the need
2. For the safety of the consumer. to keep the study secret, may favor a sample
►For example, there are some products, such as over a census.
airplanes or heart defibrillators, in which the
performance of such is so critical to the consumer
that 100% of the products are tested, and sampling
is not a reasonable option.
In both cases sampling errors are not affordable
9 10

Reasons for Sampling Reasons for Taking a Census

• Sampling – A means for gathering useful • Eliminate the possibility that a random
information about a population sample is not representative of the
– Information gathered from sample, and population.
conclusions drawn
• The person authorizing the study is
• Sampling vs. census has advantages uncomfortable with sample information.
– Sampling can save money.
– Sampling can save time.

11 12
Sample versus Census The sampling design process

Define the target Population

Determine the Sampling Frame

Select Sampling Technique(s)

Determine the Sample Size

Execute the Sampling Process

Validate the Sample

13 14

Define the target population Define the target population

►Sampling design begins by specifying the target ►Defining the target population involves
population. translating the problem definition into a precise
►Target population is the collection of elements statement of who should and should not be
or objects that possess the information sought included in the sample.
by the researcher and about which inferences ►The target population should be defined in
are to be made. terms of:
►The target population must be defined precisely. ►Elements

►Imprecise definition of the target population will ►Sampling units

result in research that is ineffective or ►Extent

misleading. ►Time
15 16
 Define the target population Define the target population
►An element is the object about which or from ► Suppose that Revlon wanted to assess consumer
which the information is desired. response to a new line of lipsticks and wanted to
►In survey research, the element is usually the sample females over 20 years of age. It may be
respondent. possible to sample females over 20 directly, in which
case a sampling unit would be the same as an
►A sampling unit A single element or group of element.
elements subject to selection in the sample.
► Alternatively, the sampling unit might be
(example on next slide). households. In the latter case, households would be
►Extent refers to the geographical boundaries of sampled and all females over 20 in each selected
the research household would be interviewed. Here, the sampling
►Time refers to the period under consideration. unit and the population element are different.
17 18

Define the target population Define the target population

► For example, if an airline wishes to sample ► If the target population has first been divided
passengers, it may take every tweny‐fifth name into units, such as households or airline flights,
on a complete list of passengers. In this case the additional terminology must be used.
sampling unit would be the same as the element. ► A unit selected in the first stage of sampling is
► Alternatively, the airline could first select certain called a primary sampling unit (PSU).
flights as the sampling unit and then select ► A unit selected in a successive stages of sampling
certain passengers on each flight. In this case is called a secondary sampling unit or (if three
the sampling unit would contain many stages are necessary) tertiary sampling unit
elements.

19 20
Define the target population Determine the sampling frame
► A sampling frame is a representation of the elements
Marketing Survey for Cars of the target population.
Elements Male aged 25–40 ► It consists of a list or set of directions for identifying
the target population.
Sampling
Households ► Sampling Frame is also called working population.
units
► Examples of a sampling frame includes:
States of Delhi, U.P., Haryana, o Telephone directory
Extent
Rajasthan and Punjab o Business directory listing the firms in an industry
Time Apr‐Sep 2023 o Customer database
o A map
21 22

Determine the sampling frame Determine the sampling frame

► Every research study has a target population that
►If a list cannot be compiled, then at
consists of the individuals, institutions, or entities that
least some directions for identifying are the object of investigation.
the target population should be
► The sample is taken from a population list, map,
specified, such as random-digit dialing directory, or other source used to represent the
procedures in telephone surveys. population.
► This list, map, or directory is called the frame, which
can be telephone directory or trade association lists.
► Ideally, a one‐to‐one correspondence exists between
the frame units and the population units. In reality, the
frame and the target population are often different.
23 24
 Determine the sampling frame Determine the sampling frame
► For example, suppose the target population is all ► Frames that have over‐registration contain the target
families living in Delhi. population units plus some additional units.
► A feasible frame would be the residential pages of the ► Frames that have under‐registration contain fewer units
Delhi telephone books. than does the target population.
► How would the frame differ from the target population? ► Sampling is done from the frame, not the target
► Some families have no telephone. population.
► Other families have unlisted numbers. ► In theory, the target population and the frame are the
► Still other families might have moved and/or changed same.
numbers since the directory was printed. ► A business researcher’s goal is to minimize the
► Some families even have multiple listings under differences between the frame and the target
different names. population.
25 26

Select a sampling technique Select a sampling technique

► The alternative sampling plans may be grouped into two
►Sampling with replacement A sampling
categories: probability techniques and nonprobability
techniques. technique in which an element can be
► Probability sampling is a technique in which every included in the sample more than once.
member of the population has a known, nonzero
probability of selection.
►Sampling without replacement A
► Nonprobability sampling is a technique in which units of sampling technique in which an element
the sample are selected on the basis of personal judgment cannot be included in the sample more
or convenience; the probability of any particular member than once.
of the population being chosen is unknown. The selection
of sampling units in nonprobability sampling is quite
arbitrary, as researchers rely heavily on personal judgment.
27 28
 Determine the sample size Determine the sample size
► Sample size refers to the number of elements to be Importance of the decision
included in the study. ► For more important decisions, more information is
► Determining the sample size involves several qualitative necessary, and that information should be obtained very
and quantitative considerations. precisely.
► Important qualitative factors to be considered in ► This calls for larger samples, but as the sample size
determining the sample size include increases, each unit of information is obtained at greater
1. Importance of the decision 6. Incidence rates cost.
2. Nature of the research 7. Completion rates ► The degree of precision may be measured in terms of the
3. Number of variables 8. Resource constraints standard deviation of the mean, which is inversely
4. Nature of the analysis proportional to the square root of the sample size. The
larger the sample, the smaller the gain in precision by
5. Sample sizes used in similar studies
increasing the sample size by one unit.
29 30

Determine the sample size Determine the sample size

Nature of the research Number of variables
► Nature of the research also has an impact on the ► If analysis of the data using multivariate techniques is
sample size. For exploratory research designs, such as required, the sample size should be large.
those using qualitative research, the sample size is Nature of the analysis
typically small. For conclusive research, such as
► If the data are to be analyzed in great detail, the sample
descriptive surveys, larger samples are required.
size should be large.
► If data are being collected on a large number of
Incidence rates
variables, i.e. many questions are asked in a survey,
larger samples are required. The cumulative effects of ► The sample size required should be adjusted for the
sampling error across variables are reduced in a large incidence of eligible respondents and the completion
sample. rate.

31 32
 Determine the sample size Determine the sample size
Completion rates Sample sizes used in similar studies
► Finally, the sample size decision should be guided by a
►Sample size is influenced by the average size of
consideration of the resource constraints. In any
marketing research project, money and time are limited. samples in similar studies.
►Table gives an idea of sample sizes used in
different marketing research studies.
►These sample sizes have been determined
based on experience and can serve as rough
guidelines, particularly when non‐probability
sampling techniques are used.
33 34

Determine the sample size Execute the sampling process

► Execution of the sampling process requires a
detailed specification of how the sampling design
decisions with respect to the population, sampling
unit, sampling frame, sampling technique and
sample size are to be implemented.
► For example, if households are the sampling unit,
an operational definition of a household is
needed. Procedures should be specified for empty
housing units and for call‐backs in case no one is at
home.
35 36
 Validate the sample
►Sample validation aims to account for sampling
frame error by screening the respondents in the
data collection phase.
►Respondents can be screened with respect to
demographic characteristics, familiarity, product
usage and other characteristics to ensure that THANK YOU
they satisfy the criteria for the target population.
►Screening can eliminate inappropriate elements
contained in the sampling frame, but it cannot
account for elements that have been omitted.
37 38