Unit -5 The Research Process- Sampling: Design & procedures

 
Sampling is the process of using a small or
parts of a larger population to make conclusions
about the whole population.
Sampling is one of the components of research
design.
Sampling design involves several basic questions:
•Should a sample be taken?
•If so, what process should be followed?
•What kind of sample should be taken?
•How large it should be?
•What can be done to control and adjust for non response
errors?
05/16/22 1
 5.2 Basic Terminologies in Sampling

• Population (Universe): The aggregate of all elements,

sharing some common set of characteristics that
comprises the universe for the purpose of marketing
research problem.
• Target population: the specific complete group relevant
to the research group.
• Population element: an individual member of a specific
population.
• Census: a complete enumeration of the elements of a
population or study objects.
• Sample: a subgroup of the elements of the population
selected for participation in the study.

05/16/22 2
• Sampling Frame: a representation of the elements of
the target population. It consists of a list or set of
directions for identifying the target population.
• Representative Frame: a sample that reflects the
population accurately so that it is a microcosm of the
population.
• Probability Sampling: a sampling procedure in which
each element of the population has a fixed
probabilistic chance of being selected for the sample.
• Non-Probability Sampling: sampling techniques that
do not use chance selection procedures, rather, they
rely on the personal judgment of the researcher.

05/16/22 3
• Sampling With Replacement: a sampling
technique in which an element can be
included in the sample more than once.
• Sampling Without Replacement: a sampling
technique in which an element can not be
included in the sample more than once.
• Sampling Units: a single element or group of
elements subject to selection in the sample.
(PSU)

05/16/22 4
• Primary Sampling Unit (PSU): a unit selected
in the first stage of the sampling.
• Secondary Sampling Unit (SSU): a unit
selected in the second stage of sampling.
• Sample Size: The number of elements to be
included in a study.
• Sampling Error: the difference between a
sample and the population from which it is
selected, even though a probability sample
has been selected.
05/16/22 5
• Non-Sampling Error: differences between the
population and the sample that arise either from
deficiencies in the sampling approach, such as an
adequate sampling frame or non-response, or
from such problems.
• Non –Response: a source of non-sampling error
that is particularly likely to happen when
individuals are being sampled. It occurs
whenever some members of the sample refuse
to cooperate, can not be contacted, or for some
reason can not supply the required data, because
of mental incapacity.

05/16/22 6
 Probability Sampling Vs. Non-probability Sampling
Sampling technique can be broadly classified into two
broad categories: Probability and Non-probability
sampling.
Probability Sampling Technique
• Probability sampling techniques vary in terms of
sampling efficiency. Sampling efficiency is a concept that
reflects a trade-off between sampling cost and precision.
Precision refers to the level of uncertainty about the
characteristics being measured. Precision is inversely
related to sampling errors but positively related to cost.
The greater the precision the greater the cost and most
studies require a trade –off. The researcher should strive
for the most efficient sampling design, subject to the
budget allocated.

05/16/22 7
Probability sampling techniques includes the following:
Simple Random Sampling(SRS)
• SRS is a probability sampling technique in which each
element in the population has a known and equal
probability of selection. Every element is selected
independently of every other element and the sample
is drawn by a random procedure from a sampling
frame.
• To draw a simple sample, the researcher first compiles
a sampling frame in which each element is assigned a
unique identification number.
• Probability of selection = sample size
Population Size
 

05/16/22 8
• There are different methods in simple random
sampling:
• The “blind Draw “method: involves blindly choosing
participants by their names of some other unique
designation.
• The table of random numbers method: a more
sophisticated application of simple random sampling is to
use a table of random numbers which is a listing of
numbers whose random order is assured.
• If you look at a table of random numbers, you will not be
able to see any systematic sequence of numbers regardless
of where in the table you begin and whether you go up,
down, left right, or diagonally across the entries.

05/16/22 9
 Advantages of SRS

• It embodies the requirements necessary to

obtain a probability sample and there for to
derive unbiased estimates of the population‘s
characteristics.
• It guarantees that every member of the
population has a known and equal chance of
being selected in to the sample; the resulting
sample, no matter what the size, will be a valid
representation of the population.

05/16/22 10
 Disadvantages of SRS

• To use either the blind draw or the table of random

numbers approach, it is necessary to pre designate each
population number.
• In the blind draw sample, each student’s name
was written on a 3-by-5 card,
• Where as in the random numbers example, each
student was a specific number.

05/16/22 11
• In essence, simple random sampling necessarily
begins with a complete listing of the population,
a current and complete listings are often
difficult to obtain.
• It is also cumbersome to provide unique
designation s for each population member.
• Numbering from 1 through an unknown total
population size (N) is tedious and invites
administrative errors.
• Using names is unsatisfactory due to duplicates.

05/16/22 12
Systematic Sampling (SS)
• SS is a probabilistic sampling technique in which
the sample is chosen by selecting a random
starting point and then picking every point and
then picking every ith elements in succession from
the sampling frame.
• A ss involves selecting every nth unit after a random
start.
• To use systematic sampling the researcher
decides on a “skip interval”, which is calculated
by dividing the number of names on the list by
sample size.

05/16/22 13
Skip interval ( I) = Population list size
Sample size

• For example, there are 100,000 elements in the

population and a sample of 1000 is desired.
• In this case, the sampling interval, I, is 100.
Random number between 1 and 100 is selected.
• If, for example, this number is 23, the sample
consists of elements 23,123, 233, 423, 523, and
so on.

05/16/22 14
 Prerequisites of Systematic Sampling
• A prerequisite for applying systematic sampling is
that the units in the population can be ordered in
some way:
• Some examples are presented below:
• Records that are ordered in a file.
• Names that are ordered alphabetically in a
telephone directory.
• Houses that are ordered along a road.
• Customers who walk one by one through an
entrance, and so on.

05/16/22 15
 Advantages

• It has “economic efficiency” (can be applied with

less difficulty.)
• The method is simple, but probably the most
important advantage is that a frame is not always
needed.
• The method can therefore be used, for instance,
to interview a sample of persons passing by a
corner during a particular day.
• The units in the sample will be spread evenly
over the ordered population. (Sometimes this will
increase precision.)
05/16/22 16
• It can be accomplished in a shorter time
period than can simple random sampling.
• It has the potential to create a sample that is
almost identical in quality to samples created
from simple random sampling.

05/16/22 17
 Disadvantages

• The most important potential drawback is the

danger of hidden periodicities, for example,
that a deficiency in producing a specific
product occurs at specific intervals.
• If one happens to get an unfortunate starting
point the whole sample could consist of
defective products.

05/16/22 18
 Stratified Sampling
• SS is a probability sampling technique that uses a two-
step process to partition the population into sub
populations, or strata. Elements are selected from
each stratum by random procedures.
• The strata should be mutually exclusive and
collectively exhaustive in that every population
elements should be omitted.
• Next, elements are selected from each stratum by
random procedures, usually SRS.
• Technically, only SRS should be employed in selecting
the elements from each stratum.
05/16/22 19
• In practice , sometimes systematic sampling
and other probability sampling procedures
are employed
• Stratified sampling differs from quota
sampling in that sample elements are selected
probabilistically rather than based on
convenience or judgment.
• A major objective of stratified sampling is to
increase precisions without increasing cost.

05/16/22 20
• Stratified sampling can be further divided into
two:
Proportionate
– In proportionate stratified sampling the size of the
sample drawn from each stratum is proportionate to
the relative size of that stadium in the total
population.
Disproportionate:
– in disproportionate stratified sampling , the size of
the sample from each stratum is proportionate to the
relative size of the stratum and to the standard
deviation of the distribution of the characteristics of
interest among all the elements in that stratum.

05/16/22 21
The logic behind disproportionate sampling is simple.
• First, strata with relative larger sizes are more
influential in determining the population mean, an d
these strata should also exert a greater influence in
delivering the sample elements. Consequently more
elements will be drawn from strata of larger relative
size.
• Second, to increase precision more elements should be
drawn from strata with larger standard deviations and
fewer elements should be drawn strata with smaller
standard deviations.
• For example, large retail stores might be expected to
have greater variation in the sales of some products as
compared to small stores.
• Hence, the number of large stores in a sample may be
disproportionately large.

05/16/22 22
 Advantages
• Stratified random sampling can give higher
precision with the same sample size,
alternatively, the same precision with a
smaller sample.
• Stratified sampling can also give separate
results for each stratum.
• Stratified sampling can also simplifies data
collection.

05/16/22 23
Disadvantages

• A complete frame is needed.

• Depending on the allocation principle applied,
additional information, such as knowledge of
standard deviations and costs, may be needed
for each stratum.

05/16/22 24
 Cluster Sampling
• Is a probability sampling in which the population is
divided into sub-groups, each of which represents
the entire population.
• In cluster sampling,
• First, the target population is divided into mutually
exclusive and collectively exhaustive subpopulations called
clusters.
• Then, a random sample of clusters is selected based on a
probability sampling technique such as simple random
sampling.
• For each selected cluster, either all the elements are
included in the sample or a sample of elements is drawn
probabilistically.

05/16/22 25
• There are three types of cluster sampling:
• One -stage sampling
• Two -stage sampling
• Multistage sampling
• A common form of cluster sampling is area
sampling.
• Area sampling is a common form of cluster
sampling in which the clusters consist of
geographic area such as counties, housing tracts,
blocks, or other area descriptions.
• In one –stage area sampling, the researcher
samples blocks and then all the households within
the selected blocks are included in the sample.
05/16/22 26
• In the case of two or multi-stage are sampling,
the researcher samples blocks, and then samples
households within the selected blocks.
Advantages
• The major advantage of cluster sampling is that
we do not need a complete frame of the
secondary sampling units. (We do not need a
frame of the clusters, however.)
• Another important advantage in many kinds of
cluster sampling such as area sampling is the
geographical concentration of the units to be
interviewed.

05/16/22 27
Disadvantages
• If there is large variation between clusters in
the variables to be examined the method may
yield poor precision.

05/16/22 28
 Sequential Sampling

• A probability sampling technique in which the

population elements are sampled
sequentially, data collection and analysis are
done at each stage, and a decision is made as
to whether additional elements should be
sampled.

05/16/22 29
• Data collection and analysis are done at each
stage, and decision is made as to whether
additional population elements should be
sampled.
• At each stage, this rule indicates whether
sampling should be continued or whether
enough information has been obtained.
• Sequential sampling has been used to
determine preferences for two competing
alternatives.
05/16/22 30
• Ate In one study, respondents were asked
which of the two alternatives they preferred,
and sampling was terminated when sufficient
evidence was accumulated to validate a
preference.
• It has also been used to establish the price
differential between a standard models a
deluxe model of a consumer durable.
•  

05/16/22 31
 Double Sampling

• A sampling technique in which certain population

elements are sampled twice.
• In the first phase, a sample is selected and some
information is collected from all the elements in the
sample.
• In the second phase, a subsample is drawn from the
original sample and additional information is obtained
from the elements in the sub sample.
• The process may be extended to three or more
phases, and the different phase may take place
simultaneously or at different times.
05/16/22 32
• Double sampling can be useful when no
sampling frame is readily available for
selecting final sampling units but when the
elements of the frame are known to be
contained within a broader sampling frame.

05/16/22 33
 Non-Probability Sampling Techniques

• The critical difference between probability and

non-probability sampling methods is the
mechanics used in the sample design.
• With non-probability sampling method, selection is
not based on probability.
• In other words you can’t calculate the probability
of any one person in the population being selected
into the sample.
• Still each non-probability sampling method strives
to draw a representative sample.

05/16/22 34
 Non -Probability Sampling Methods
• The non probability sampling methods include the following:
• Convenience Sampling
• A non-probability sampling technique that attempts to obtain a
sample of convenient elements. The selection of sampling units is
left primarily to the interviewer.
• Examples of convenience sampling includes:
• Use of students , church groups , and members of social
organisations
• Mall-intercept interviews without qualifying the
respondents
• Department stores using charge accounts lists,
• Tear-out questionnaires included in a magazine, and
• “People on the street” interviews.

05/16/22 35
• The non probability sampling methods include the
following:
• Convenience Sampling
• A non-probability sampling technique that attempts to
obtain a sample of convenient elements. The selection of
sampling units is left primarily to the interviewer.
• Examples of convenience sampling includes:
• Use of students , church groups , and members of
social organisations
• Mall-intercept interviews without qualifying the
respondents
• Department stores using charge accounts lists,
• Tear-out questionnaires included in a magazine,
and
• “People on the street” interviews.

05/16/22 36
• Convenience samples are not recommended for
descriptive or causal research , but they can be
used in exploratory research for generating
ideas, insights, or hypothesis
• Convenience samples can used for focus groups ,
pretesting questionnaires , or pilot studies.
• Even in these cases, caution should be exercised
in interpreting the results.
• Nevertheless, this technique is sometimes used
even in large surveys.

05/16/22 37
Judgment Sampling
• A form of convenience sampling in which the
population elements are purposely selected
based on the judgment of the researcher.
• The researcher uses his or her judgment or that
of some other knowledgeable person to identify
who will be in the sample.
• Subjectivity enters in here, and certain members
of the population will have a smaller chance of
selection than will others.
• The researcher exercising common examples of
judgment sampling include :
05/16/22 38
• judgment or expertise , chooses the elements to be
included in the sample , because he or she believes
that they are representative of the population of
interest or are otherwise appropriate.
• Test markets selected to determine the
potential of a new product.
• Purchase engineers selected in industrial
marketing research because they are
considered to be representative of the
company
• Bellwether precincts selected in voting
behaviour research,
• Department stores selected to test a new
merchandising display system.

05/16/22 39
 Referral Samples/Snowball Samples

• Respondents are asked for the names or identities of

other s like themselves who might qualify to take part
in the survey.
• A non probability sampling technique in which an
initial group of respondents is selected randomly.
• Subsequent respondents are selected based on the
referrals or information provided by the initial
respondents.
• This process may be carried out in waves by obtaining
referrals from referrals.
• A major objective of snowball sampling is to estimate
characteristics that are rare in the population.

05/16/22 40
• Examples include users of particular
government or social services , such as food
stamps, whose names can’t be revealed;
special census groups, such widowed males
under 35; and members of a scattered
minority population.
• Snowball sampling is used in industrial buyer –
seller research to identify buyer- seller pairs.

05/16/22 41
Advantages
– It substantially increases the likelihood of locating
the desired characteristics in the population.
– It also results in relatively low sampling variance
and costs.

Quota Samples
– A non-probability sampling technique that is a
two-stage restricted judgmental sampling.
– The size of the quotas is determined by the
researcher’s belief for the relative size of each
class of respondent.

05/16/22 42
• The first stage consists of developing control
categories or quotas of population elements.
• In the second stage, sample elements are
selected based on convenience sampling.
• To develop these quotas, the researcher lists
relevant control characteristics which may
include sex, age and race, are identified on
the basis of judgment.
• A field worker is provided with screening
criteria that will classify the potential
respondent into a particular quota cell.

05/16/22 43
• For example, a large bank, might stipulate that the
final sample be one-half adult males and one-half adult
females because in their understanding of their
market, the customer profile is about 50-50, male and
female.
• Often the quotas are assigned so that the proportion
of of the sample elements possessing the control
characteristics is the same as the proportion of
population elements with these characteristics is the
same as the proportion of population elements with
these characteristics.
• In other words, the quotas ensure that the
composition of the sample is the same as the
composition of the population with respect to the
characteristics of interest.

05/16/22 44
• In the second – stage, sample elements are
selected based on convenience or judgment.
• Once the quotas have been assigned, there is
considerable freedom in selecting the elements
to be included in the sample.
• The only requirement is that the elements
selected fit the control characteristics.
• In certain situations, it is desirable either to
under –or oversample heavy users of a product
so that their behaviour can be examined in detail.
• Although this type of sample is not
representative, it may nevertheless be very
relevant.
05/16/22 45
Advantages
• QS Attempts to obtain representative samples at
a relatively low cost.
• A quota system overcomes much of the non-
representative ness danger inherent in
convenience samples.
• It may guarantee that the researcher has
sufficient sub-sample sizes for meaningful
subgroup analysis.
• Under certain conditions, quota sampling obtain
results close to those for conventional probably
sampling.

05/16/22 46
 Strengths and Weaknesses of probability Sampling Techniques

S/N Technique Strengths Weaknesses

1 Simple random sampling (SRS) Easily understood, result Difficult to construct

projectable sampling frame , expensive ,
lower precision, no
assurance of
representativeness

2 Systematic sampling Can increase representativeness , Can decrease

easier to implement than SRS, representativeness
sampling frame not necessary

3 Stratified sampling Includes all important Difficult to select relevant

subpopulations, precision stratification variables , not
feasible to stratify on many
variables , expensive

4 Cluster sampling Easy to implement cost effective Imprecise, difficult to

compute and interpret
results.

05/16/22 47
 Strengths and Weaknesses of Non-probability Sampling Techniques

S/N Technique Strengths Weaknesses

1 Convenience sampling Least expensive , least time consuming, Selection bias , sample not representative
most convenient , not recommended for descriptive or
causal research

2 Judgment sampling Low cost, convenient, not time Does not allow generalization , subjective
consuming

3 Quota sampling Sample can be controlled for certain Selection bias , no assurance of
characteristics representativeness

4 Snow ball sampling Can estimate rare characteristics. Time consuming

05/16/22 48
 Choosing Probability versus Non - Probability sampling
S/N Factors Probability Sampling Non-Probability Sampling

1 Nature of research Conclusive Exploratory

2 Relative magnitude of Sampling errors are Non-sampling errors are

sampling and non larger larger
sampling errors

3 Versatility in the Heterogeneous (high) Homogeneous (low)

population
4 Statistical Favorable Unfavorable
considerations

5 Operational Unfavorable Favorable

considerations

05/16/22 49
 Procedures for Drawing Probability Sampling
Simple Random Sampling
• Select a suitable sampling frame
• Assign each element a number 1 to N (population size)
• Generate n (sample size) different random numbers
between 1 and N. This can be done using a
microcomputer or mainframe software package or using
a table of simple random numbers. Arbitrarily select a
beginning numbers. Select the appropriate number of
digits (For Example: if N=900, select three digits).Then
proceed either up or down until n different numbers
between 1 and N have been selected. Note: discard 0,
duplicate numbers, and numbers greater than N.
• The numbers generated denote the elements that
should be included in the sample.
•  
05/16/22 50
Systematic Sampling
• Select a suitable sampling frame.
• Assign each element a number 1 to
N( population size)
• Determine the sampling interval, I, i= N/n, if I is
a fraction, round to the nearest integer.
• Select a random number, r, between 1 and I, as
explained in simple random sampling.
• The elements with the following numbers will
comprise the systematic random sample: r, r+1,
r+2i, r+3i, +4i,…..r+(n-1)i.
05/16/22 51
 Stratified Sampling
 
• Select a suitable sampling frame.
• Select the stratification variable (s) and the number of
strata (H).
• Divide the entire population into H strata. Based on the
classification variable, assign each element of the
population to one of the H strata.
• In each stratum, the number the elements from 1 to N h
(the population size of stratum h ).
• Determine the sample size of each stratum, n h, based on
proportionate or
• Disproportionate ………………..
• In each stratum, select a sample random sample of size n h.
05/16/22 52
 Cluster Sampling
• We describe the procedure for selecting a simple two-stage sample, because this
represents the simpler case.
• Assign a number, from 1 to N, to each element in the population.
• Divide the population into C clusters, of which c will be included in the sample.
• Calculate the sampling interval, I, i= N/c. If it is a fraction, round to the nearest
integer.
• Select a random number, r, between 1 and I, as explained in simple random
sampling.
• Identify elements with the following numbers: r, r+1, r+2i, r+3i, ….., r+(c-1) i.
• Select the cluster that contains the identified elements.
• Select sampling units within each selected cluster based on SRS or systematic
sampling. The number of sampling units selected from each sample cluster is
approximately that same and equal to n/c.
• .

05/16/22 53
• If the proportion of a cluster exceeds the sampling
interval, I, that cluster is selected with certainty.
That cluster is removed from further
consideration. Calculate the new population size,
N*, number of clusters to be selected, C* (=c-1),
and the new sampling interval, i*. Repeat this
process until each of the remaining clusters has a
population less than the relevant sampling
interval. If b clusters have been selected with
certainty, select the remaining c-b clusters
according to steps 1 through 7 . The fraction of
units to be sampled from each cluster selected
with certainty is the overall sampling fraction
=n/N

05/16/22 54
• Thus, for clusters selected with certainty we
would select ns =n/N (N1 +N2 + . . . + Nb) units.
The units selected from clusters selected
under two-stage sampling will therefore be
n*= n-ns

05/16/22 55
 Developing a sample plan

• The various aspects of sampling are logically joined

together and has a definite sequence or steps
presented as follows:
– Step 1: Define the relevant population.
– Step 2: Obtain the “listing of the population.
– Step 3: Design the sample plan (size, method).
– Step 4: Access the population
– Step 5: Draw the sample.
– Step 6: Validate The Sample.
– Step 7: Resample, If Necessary.

05/16/22 56
 Method of Determining the Sample Size

• The following methods include the following:

Arbitrary Approach:
• Uses a “rule of thumb “to determine the sample
size.
• The researcher may determine, for instance, the
sample size should be 5% of the population.
• Arbitrary sample size are simple and easy to
apply, but they neither efficient not economical.

05/16/22 57
 Conventional Approach:
• It follows some “convention”, number believed
somehow to be the right sample size.
• The convention might be an average of the sample
sizes of similar studies,
• it might be the largest sample size of previous surveys,
or
• it might be equal to the sample size of a competitor’s
survey.
• For instance, the researcher may take the conventional
sample size of between 1000 and 1200 as determined
by the industry.
• Use of a conventional sample size can result in a
sample that may be too small or too large.

05/16/22 58
 Cost Analysis

• It uses cost as a basis for sample size.

• In this case instead of the value of the
information to be gained –from survey being a
primary consideration in the sample size, the
sample size is determined by cost factors that
ignore the value.

05/16/22 59
 Statistical Approach

• Some advanced statistical techniques require

certain minimum sample size in order to be
reliable, or to safeguard the validity of the
statistical results.
• Statistical analysis is used to analyse
subgroups within a sample.

05/16/22 60
 Confidence Internal Approach

• To create a valid sample, the confidence interval

approach applies the concepts of:
• Variability
• Confidence interval
• Sampling distribution , and
• A standard error of a mean.
• Variability: is the amount of dissimilarity in
respondent’s answers to a particular question.
• Confidence interval: is a large whose end points define a
certain percentage of the responses is a question:

05/16/22 61
• Standard Error: it indicates how far away
from the true population value a typical
sample result is expected to fall:
• There are two ways to compute a
standard error:
• The standard error of the mean
• The slandered error of a percentage

05/16/22 62