1

Sampling terminology
• A sample is a subset of a larger population.
– The purpose of sampling is to estimate an unknown
characteristic of a population.

• A population is any complete group—for example, of people,

sales territories, stores, or college students.
– Shares some common set of characteristics.

• Census survey is the complete enumeration of all items or

objects in a population under study.

• Sample survey is the enumeration of a portion of all objects

under any study
2
 Distinction between Census and Sample survey

• Enumeration
• Time and Cost needed
• Quality of personnel
• Quality of data
• Special purpose

3
 Merits of sample survey
• Accurate and Reliable Results: Sample may on occasion be
more accurate than a census since non sampling errors may
increase during because of the increased volume of work.

• Destruction of Test Units: Especially those in quality-control

testing, require the destruction of the items being tested. For
example, testing bulbs, blood count.

4
 Steps involved in a Sample Survey
1. Aim of the Survey
2. Definition and Scope of population
3. Sampling frame and sampling unit
4. Questionnaire to be used
5. Method of data collection
6. Selection of appropriate sampling method (methods of
selecting sample from population)
7. Pilot survey (limited survey before the master survey, helps
evade errors and have the idea beforehand of the
expenditure of the master survey)
8. Field work (data collection)
9. Data analysis
5
Stages in the Selection of a Sample

6
 Stages in the Selection of a Sample
1. Defining the Target Population:

2. Sampling Frame:
A list of elements from which a sample may be drawn;
also called working population.
– A list of all members of Accounting Alumni
Association.
– In practice, almost every list excludes some members
of the population.

3. Sample size:
Determination of the sample size is another big
challenge as it has both statistical and real life
implication 7
 Stages in the Selection of a Sample
Sampling frame error: error that occurs when certain
sample elements are not listed or are not accurately
represented in a sampling frame.
For example university student e-mail directory.
– Population elements can be either under- or
overrepresented in a sampling frame.
• For example, a savings and loan defined its population as
all individuals who had savings accounts. However,
individuals who had multiple accounts were
overrepresented in the sample.

8
 Random Sampling Error
• The error that arises due to drawing inferences
about a population based on sampling is known as
sampling error.
• Is unavoidable in spite any higher degree of
cautiousness in selecting sample
• As sample size increases, random sampling
error can be minimized.
• In census survey sampling error turns to zero

9
 Systematic Errors/Non - sampling error
• Sample estimate may also be affected by error other than the
sampling error is known as non sampling error.
• Loss of information/ failure to measure some of the units
• Defective measurement technique
• Lack of trained and experienced investigators
• Increase due to increase of samples( measurement, coding ,
tabulating etc)
• Both errors are inversely related

10
 Two Major Categories of Sampling
Probability sampling : A probability sampling is one for which
the inclusion or exclusion of any individual element of the
population depends upon the application of probability methods
and not on a personal judgment. Every member of the
population has a known, nonzero probability of selection. The
essential feature of drawing such a sample is the randomness.

11
 Two Major Categories of Sampling
Non probability sampling: As against the probability sample, we
have a variety of other samples, termed as judgement samples, purposive
samples, quota samples, etc. These samples have one common distinguishing
feature:

Personal judgement rather than the random procedure to determine the

composition of what is to be taken as a representative sample. The
judgement affects the choice of the individual elements.

• All such samples are non-random, and no objective measure of precision may
be attached to the results arrived at.

– Probability of selecting any particular member is unknown.

– Researchers rely heavily on personal judgment.
– No appropriate statistical techniques exist for measuring random sampling
error from a non probability sample.

12
 Random Sampling

• Simple random sampling

• Systematic sampling
• Stratified sampling
• Cluster sampling

13
13
 Simple random sampling

• In simple random sampling, drawing of elements from the

population is random
• The choice of an element is made in such a way that every
element has the same probability of being chosen.
• When the sample is so selected, every possible set of
elements has the same chance of being drawn.
• Methods of drawing simple random sample:
- Lottery method
- Use of random number tables
• No bias, required complete list of the population
• the population to be sampled is treated as homogeneous
14
 Stratified random sampling

• In stratified random sampling, the population is sub-divided

into strata before the sample is drawn. The Strata should be
non overlapping and together comprise the entire population.
• The strata should be homogenous within the group but
heterogeneous across the group.
• Strata: Dividing the population into subgroups.
• Stratum: Each subgroup is known as stratum.
• Then a subsample is drawn using simple random sampling
within each stratum.

15
 Stratified random sampling

There are four methods of allocation of sample sizes to different

Strata.
1. Equal allocation: Total sample size n is equally divided among
all strata

2. Proportional allocation: In this method select the sample size

proportional to the corresponding stratum size. i.e if the
stratum size is larger than the sample will be obtained from
that strata and vice versa.

16
 Stratified random sampling

3. Optimum allocation: The number of units to be selected

from different strata are determined with the view to
minimize
- The sampling variance for a given cost
- The cost in the survey for a predetermined value of
sampling variance
.4. Neymen allocation: When the sampling cost among strata is
equal then the optimum allocation turns to be Neymen
allocation.
this method of allocation is considered to be the more
efficient than proortional allocation.

17
 Cluster Sampling

• A cluster is a group of individuals or objects having different

characteristics.
• In a cluster sampling the clusters are so formed as there be the
maximum heterogeneity within cluster and homogeneity
between cluster to cluster.
• Cluster either be of equal size (math boxes) or of uneual size
( family income)
• Sampling carried out in different stages. In first stage, the whole
population is divided into some sampling units depending on
problem under study then the units are divided again into some
regeionable sub units or sub groups.
• Then observe every unit in the selected sub groups(cluster)
• Known as multi stage sampling 18
 Cluster Sampling

• The primary sampling unit is not the individual element in the

population but a large cluster of elements; clusters are
selected randomly.
• Economical while retains the characteristics of a probability
sample.
– Consider a researcher who must conduct five hundred
personal interviews with consumers scattered throughout
Bangladesh. Travel costs and time are likely to be
enormous. If the product equally appeals dwellers of
Dhaka and Chittagong then only one cluster can be
interviewed.
• Ideally a cluster should be heterogeneous.

19
 Cluster sampling

Merits:
• Easier ,cheaper and less time consuming.
• Cluster sampling requires less cost than simple random
sampling and Stratified random sampling
• In case of non availability of complete and up to date
sampling frame can be used.
Demerits:
• Provide Less efficient variances
• Proper clustering difficult, sampling error is high

20
 Systematic Sampling
• Sampling units are selected at equal distances in the list of all
the units of the population. This method is widely used when
a complete list of the population is available.
• A starting point is selected by a random process and then
every nth number on the list is selected.
• Is not a random sampling although the first element I selected
at random. Is also known as quasi random sampling
• Linear systematic sampling: Population size N is divisible by
the desired sample size; N/n= k = 500/50= 10=integer)
• Circular systematic sampling( N is not divisible by the desired
sample size)

21
i) Linear systematic sampling: Population size N is divisible by the desired
sample size n. Linearity means the population is linearly ordered in a way
that its units can be referred to by subsequent numbers without ambiguity.

Here 1st unit i is selected at random ,in such a way that 1< i < k.
i.e; N/n= k = 500/50= 10=integer
Therefore the sample of size n would be the aggregation of following units.
i, i+k, i+2k, i+3k, ……… ,i+(n-1)k
Let i=4, then If the 1st item selected for our desired sample is the 4th item on
the list

ii)Circular systematic sampling: N is not divisible by the desired sample size

22
 Systematic Sampling

• Suppose a researcher wants to take a sample of 1,000 from a

list of 200,000 names. With systematic sampling, every 200th
name from the list would be drawn.
• easiest method, convenient than other sampling
• For sufficiently large population provide same results like
other
• Requires up to date sampling frame.

23
 Nonprobability Sampling

• Convenience
• Judgment
• Quota
• Snowball

24
 Convenience Sampling
• The sampling procedure of obtaining the people or units that are
most conveniently available. Is collected for readily available list.
Ex- automobile registration, telephone directories etc.
– For example, television stations often present person-on-the-
street interviews that are presumed to reflect public opinion
• Is useful for plot survey. We cannot know whether our sample
units are representative or not. Result is biased and ot
satisfactory.
• Used to obtain a large number of completed questionnaires
quickly and economically.
– Also called haphazard or accidental sampling

25
 Judgment Sampling
• An experienced individual selects the sample based on
his or her judgment about some appropriate
characteristics required of the sample member.
– Also called purposive sampling.
– For example the consumer price index (CPI) is based
on a judgment sample of market-basket items,
housing costs, and other selected goods and services.
• Researchers select samples that satisfy their specific
purposes, even if they are not fully representative.
– Judgment sampling often is used when the sample
size is small or the no of sampling units in the
population is small, in pilot survey and in solving
business problem and disease related study.
26
 Quota Sampling
Quota sampling is one type of judgement sampling and is the
Widely used sampling technique in non random sampling.
here quotas re set up according to specific characters and
then the sample units are selected from the quota’s by
judgement. Very similar to stratified sampling.
– For example, an interviewer in a particular city may be
assigned 100 interviews, 35 with owners of Sony TVs, 30
with owners of Samsung TVs, 18 with owners of Panasonic
TVs, and the rest with owners of other brands.
– Used in public opinion studies. Need sincere field
representative , otherwise difficult to execute perfect study.

27
 Snowball Sampling
• In sociology and statistics research, snowball sampling (or chain sampling,
chain-referral sampling, referral sampling) is a non probability sampling
technique where existing study subjects recruit future subjects from
among their acquaintances. Thus the sample group is said to grow like a
rolling snowball.

• As sample members are not selected from a sampling frame, snowball

samples are subject to numerous biases. For example, people who have
many friends are more likely to be recruited into the sample. When virtual
social networks are used, then this technique is called virtual snowball
sampling.

• Snowball sampling is a recruitment technique in which research

participants are asked to assist researchers in identifying other potential
subjects.

28
Stratified Sampling

29
30
31
 Problem

The following data are the results of a market survey with a sample size 50
Regarding the acceptability of a new product which the company wants to
launch. The scores of the respondent on the appropriate scales are as follows:

40 45 41 45 45 30 39 8 48 12

26 23 24 26 29 8 40 41 42 36
27 35 18 25 35 40 42 43 44 09
28 27 32 28 27 25 26 38 37 25
29 35 32 28 40 41 43 44 45 40

i) Draw a simple random sample of size 10 using the above data, then find their
mean and variance.
ii) Draw a stratified random sample of 15 from the above population. Stratified the
population
• 32
 Problem

i)Draw a simple random sample of size 10 using the above data, then find
their mean and variance.
ii) Draw a stratified random sample of 15 from the above population.
Stratified the population into two groups. a) less than 30 b) greater than or
equal to 30 or more
iii) Draw a systematic sample of 6 from the population.

33