Unit 3

Chapter 2:
Sampling Design
 Census and Sample Survey

All items in any field of inquiry

constitute a ‘Universe’ or
‘Population.’
 Census Survey

 A complete enumeration of all items in the ‘population’ is known as a

census inquiry.
 It can be presumed that in such an inquiry, when all items are covered, no
element of chance is left and highest accuracy is obtained.
 This type of inquiry involves a great deal of time, money and energy.
 Therefore, when the field of inquiry is large, this method becomes difficult
to adopt because of the resources involved.
 At times, this method is practically beyond the reach of ordinary
researchers.
 Perhaps, the government is the only institution which can get the
complete enumeration carried out, once in a decade.
 Sample Survey
 When field studies are undertaken in practical life, considerations of time
and cost almost invariably lead to a selection of respondents i.e., selection
of only a few items.
 The respondents selected should be as representative of the total
population as possible in order to produce a miniature cross-section.
 The selected respondents constitute what is technically called a ‘sample’ and
the selection process is called ‘sampling technique.’ The survey so conducted
is known as ‘sample survey’.
 Algebraically, let the population size be N and if a part of size n (which is < N)
of this population is selected according to some rule for studying some
characteristic of the population, the group consisting of these n units is
known as ‘sample’.
 Researcher must prepare a sample design for his study i.e., he must plan
how a sample should be selected and of what size such a sample would be.
 Implications of a Sample Design

 A sample design is a definite plan for obtaining a sample from a

given population.
 It refers to the technique or procedure the researcher would adopt
in selecting items for the sample.
 Sample design will also decides on 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.
 Researcher must select/prepare a sample design which should be
reliable and appropriate for his research study.
 Steps in Sample Design
• 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(The population of a city, the number of workers in a
factory) or infinite(number of stars in the sky, throwing of a dice).
• Sampling unit
A decision has to be taken concerning a sampling unit before selecting sample. Sampling unit - state,
district, house, family, school, individual. Decide one or more of such units.
• 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. It is extremely important for the
source list to be as representative of the population as possible.
• Size of sample
This refers to the number of items to be selected from the universe to constitute a sample. The size of
sample should neither be excessively large, nor too small. It should be optimum. An optimum sample is
one which fulfills the requirements of efficiency, representativeness, reliability and flexibility.
 Steps in Sample Design
• Parameters of interest
In determining the sample design, one must consider the question of the specific population
parameters which are of interest. For instance, we may be interested in estimating the
proportion of persons with some characteristic in the population, or we may be interested in
knowing some average or the other measure concerning the population. There may also be
important sub-groups in the population about whom we would like to make estimates.
• 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.
• Sampling procedure
Finally, the researcher must decide about the technique to be used in selecting the items for the
sample. There are several sample designs, he must select that design which, for a given sample
size and for a given cost, has a smaller sampling error.
 Criteria of Selecting a Sampling Procedure

 Two costs are involved in a sampling analysis viz., the cost of collecting
the data and the cost of an incorrect inference resulting from the data.
 Researcher must keep in view the two causes of incorrect inferences
viz., systematic bias and sampling error.
 A systematic bias results from errors in the sampling procedures, and it
cannot be reduced or eliminated by increasing the sample size.
 At best the causes responsible for these errors can be detected and
corrected.
Criteria of Selecting a Sampling Procedure (Contd.)

Usually, a systematic bias is the result of one or more of the following factors:

 Inappropriate sampling frame :

If the sampling frame is inappropriate i.e., a biased representation of the universe, it will result in
a systematic bias.

 Defective measuring device:

If the measuring device is constantly in error, it will result in systematic bias.
• A biased questionnaire (leading questions or incomplete options).
• A physical measuring device (e.g., a faulty scale) producing incorrect readings.
Criteria of Selecting a Sampling Procedure (Contd.)

 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.
• wealthier individuals may be less likely to participate in income surveys, skewing results.

 Indeterminancy principle
Sometimes we find that individuals act differently when kept under observation than what
they do when kept in non-observed situations. Indeterminancy principle may also be a
cause of a systematic bias.
• Workers may deliberately slow down in a time-study exercise if they suspect it will lead
to increased work quotas.
Criteria of Selecting a Sampling Procedure (Contd.)
 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 government
taxation department, whereas we find an upward bias in the income data collected
by some social organisation. People in general understate their incomes if asked
about it for tax purposes, but they overstate the same if asked for social status.
Generally in psychological surveys, people tend to give what they think is the
‘correct’ answer rather than revealing their true feelings.
 Sampling errors are the random variations in the sample estimates around the true
population parameters. Sampling error decreases with the increase in the size of
the sample.
 Sampling error can be measured for a given sample design and size. The
measurement of sampling error is usually called the ‘precision of the sampling plan’.
If we increase the sample size, the precision can be improved.

While selecting a sampling procedure, researcher must ensure that the procedure causes a
relatively small sampling error and helps to control the systematic bias in a better way.
 Characteristics of a Good Sample Design

a) Sample design must result in a truly representative sample.

b) Sample design must be such which results in a small sampling error.
c) Sample design must be viable in the context of funds available for the
research study.
d) Sample design must be such so that systematic bias can be controlled in
a better way.
e) Sample should be such that the results of the sample study can be
applied, in general, for the universe with a reasonable level of
confidence.
 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.
 CHART SHOWING BASIC SAMPLING DESIGNS

• Probability Sampling is based on the concept of random selection, whereas non-probability

sampling is non-random sampling.

• When each sample element is drawn individually from the population at large, then the
sample so drawn is known as ‘Unrestricted sample’, whereas all other forms of sampling are
covered under the term ‘restricted sampling’.
 Different Types of Sample Designs

• Non-probability Sampling

– 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.
Types of Non-Probability Sampling:

1.Purposive or Judgment Sampling:

The researcher selects specific items or units based on their judgment of what constitutes a representative
sample.
Example: Choosing certain towns and villages to study the economic conditions of a state.
Advantages:
1. Quick and cost-effective for small studies.
2. Useful when domain expertise is available.
Disadvantages:
1. High risk of personal bias affecting the results.
2. Limited reliability for large-scale or critical studies.
2.Quota Sampling:
A subset of purposive sampling where the population is divided into strata (e.g., age, gender, income groups), and
interviewers are assigned quotas to fill within each group.
Advantages:
1. Convenient and inexpensive.
2. Ensures some representation from key subgroups.
Disadvantages:
1. Final sample is often subjectively selected, not random.
2. Results lack statistical robustness and are not formally generalizable.
Advantages of Non-Probability Sampling:
1. Cost-Effectiveness: Requires fewer resources and is quicker to conduct.
2. Flexibility: Can be adapted to specific research needs.
3. Feasibility: Practical for exploratory or small-scale studies.

Disadvantages of Non-Probability Sampling:

1. Risk of Bias: The personal judgment of the researcher can lead to skewed samples.
2. Lack of Generalizability: Results cannot be confidently applied to the entire population.
3. Non-Statistical Basis: Sampling errors and biases cannot be formally measured or
corrected
4. Limited Use in Large Studies: Rarely adopted for significant inquiries where precision and
reliability are critical.

Applications:
1. Small-Scale Studies: Ideal for pilot studies, exploratory research, or situations with
limited resources.
2. Preliminary Research: Useful for generating hypotheses and understanding trends
before larger studies.
3. Convenience Sampling: Situations where representative sampling is not feasible due to
constraints of time, budget, or access.
 Different Types of Sample Designs
• Probability Sampling

– Probability sampling is also known as ‘random

sampling’ or ‘chance sampling’.

– Under this, every item of the universe has an equal chance of inclusion in the
sample.

– 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.
Types of Probability Sampling:

1.Simple Random Sampling:

Each element in the population has an equal chance of selection.

For example: Random selection of 20 students from class of 50 student. Each student has equal chance of getting
selected. Here probability of selection is 1/50

2.Sampling With and Without Replacement:

1. Without Replacement: Once an item is selected, it is not returned to the population for further selection.
2. With Replacement: Selected items are returned to the population before subsequent selections, allowing the
same item to be chosen more than once.
3.Stratified Random Sampling:
Population is divided into subgroups (strata) based on certain characteristics, and random samples are taken
from each stratum.

4.Systematic Sampling:
Selecting every kth item from a list, where k is a fixed interval.

5.Cluster Sampling:
Dividing the population into clusters and randomly selecting entire clusters for study.

6.Multi-Stage Sampling:
A complex form of cluster sampling conducted in multiple stages.
 How to Select a Random Sample?
• Random sampling involves ensuring that each element in the
population has an equal and independent chance of being selected.
• Below are methods and procedures for selecting a random sample in
practice.
• Lottery Method
• Successive Drawing without Replacement
• Using Random Number Tables
• a. Lottery Method
• Process:
• Write each element of the population on a slip of paper.
• Place all slips into a container.
• Mix thoroughly and draw slips one by one without looking until the
required sample size is reached.
• Drawbacks:
• Impractical for large or complex populations.
• Limited utility in modern, large-scale sampling scenarios.
How to Select a Random Sample? (Contd..)
b. Successive Drawing without Replacement
How to Select a Random Sample? (Contd..)
c. Using Random Number Tables

Random number tables (e.g., Tippett’s Table) are pre-constructed

datasets of random digits. Each element of the population is assigned a
unique number.

• Identify the range of population numbers (e.g., 3001 to 8000).

• Read the table sequentially to select numbers within the specified
range
• For example, from Tippett’s table, selecting 10 random numbers:
Numbers like 3992, 6641, 7979, etc., form the random sample.
 Random Sample From An Infinite Universe
An infinite population refers to a scenario where the population size is too large or
indefinite to enumerate (e.g., all possible outcomes of a random experiment).

A random sample from an infinite population ensures that:

• Each selection is controlled by the same probabilities.
• Successive selections are independent of each other.

Examples of Random Sampling in Infinite Populations

Rolling a Dice
Imagine a hypothetically infinite population of outcomes from rolling a fair six-sided dice.
We roll the dice 20 times, treating the results as a sample.

The 20 dice rolls constitute a random sample from the infinite population of all possible
dice rolls.
 Complex Random Sampling Designs
1. Systematicsampling

2. Stratified sampling

3. Clustersampling

4. Areasampling

5. Multi-stage sampling

6. Samplingwith probability proportional tosize

7. Sequential sampling
Complex Random Sampling Designs(Contd..)
• Systematic sampling

– Systematic sampling is a practical method of sampling where items are

selected at regular intervals from a list or population. To introduce
randomness, the starting point of the selection process is chosen
randomly
– Random Start: A random number is used to determine the starting
point within the first k elements, where k is the interval determined by
the desired sample size.

– Fixed Intervals: After selecting the first item, every k-th item is included
in the sample. For instance, if a 4% sample is needed, k will be 25 (as 4%
of 100 is 1/25). The first item is selected randomly from the first 25, and
then every 25th item is added to the sample.
Complex Random Sampling Designs (Contd..)
Stratified sampling

• A sampling technique used when the population is not homogeneous.

• Ensures the sample is representative of the population.
• Divide the population into homogeneous sub-populations (strata).
• Select samples from each stratum.

Example:
A study on education levels may divide the population by age group,
gender, or location.
Complex Random Sampling Designs(Contd..)
Stratified sampling

The following three questions are highly relevant in the context of stratified
sampling:

a) How to form strata?

b) How should items be selected from each stratum?
c) How many items be selected from each stratum or how to allocate the
sample size of each stratum?
 Complex Random Sampling Designs(Contd..)

How to form strata?

Ensure homogeneity within each stratum and heterogeneity between different
strata.
•Approach:
• Form strata based on common characteristics (e.g., age groups, income
levels, geographic regions) that are relevant to the study.
• Leverage past experience and personal judgment for initial stratification.
• Consider the relationship between:
• Characteristics of the population.
• Characteristics to be estimated.

•Pilot Studies:
• Conduct small-scale surveys to test proposed strata.
• Evaluate variances within and between strata to refine the stratification plan.
• A careful stratification plan improves sampling efficiency by reducing
sampling error.
 Complex Random Sampling Designs(Contd..)
How Should Items Be Selected From Each Stratum?
• The selection method within each stratum typically involves:
• Simple Random Sampling: Ensures every item in the stratum has an
equal chance of selection.
• Systematic Sampling: Can be employed when it offers logistical or
analytical advantages over random sampling.
• The choice depends on the research context, the nature of the population,
and available resources.

How to Allocate the Sample Size to Each Stratum?

This part wasn't covered in detail in your excerpt, but it typically involves:
• Proportional Allocation: The sample size for each stratum is
proportional to its size in the population.
• Optimal Allocation: Factors in variability within strata and costs of
sampling to allocate sample sizes efficiently.
Proportional Allocation
Optimal Allocation (Disproportionate Sampling):
 Complex Random Sampling Designs(Contd..)

• Cluster sampling

Thus in cluster sampling the total population is divided into a

number of relatively small subdivisions which are themselves
clusters of still smaller units and then some of these clusters are
randomly selected for inclusion in the overall sample.

• Area sampling

If clusters happen to be some geographic subdivisions, in that

case cluster sampling is better known as area sampling
 Complex Random Sampling Designs(Contd..)

• Multi-stage sampling

– Multi-stage sampling is a further development of the principle of

cluster sampling.

• Sampling with probability proportional to size

– In case the cluster sampling units do not have the same number of
elements, it is considered appropriate to use a random selection
process where the probability of each cluster being included in the
sample is proportional to the size of the cluster.
 Complex Random Sampling Designs(Contd..)

• Sequential sampling
– This sampling design is some what complex sample design.
– The ultimate size of the sample under this technique is not fixed
in advance, but is determined according to mathematical
decision rules on the basis of information yielded as survey
progresses
The following are the number of departmental stores in 15 cities: 35, 17, 10, 32, 70, 28, 26, 19,
26, 66, 37, 44, 33, 29 and 28. If we want to select a sample of 10 stores, using cities as clusters
and selecting within clusters proportional to size, how many stores from each city should be
chosen? (Use a starting point of 10).

Step-by-Step Solution:

1. Total Number of Stores (N):

The total number of stores in all cities combined is the sum of the stores in each city:

2. Total Sample Size (n): You need to select a sample of 10 stores from these 500 stores.

3. Sampling Interval (k): To select the sample proportional to the size of the cities, we need
to calculate the sampling interval (k), which is the number of stores in the population divided
by the sample size:

This means we will select every 50th store.

4. Start Point: The starting point for the sampling is given as 10.
5. Cumulative Totals: First, calculate the cumulative total of stores for each city,
which represents the running total of the number of stores as you move through the
cities.
6. Selecting the Stores: Starting from 10, we add 50 each time (the sampling
interval), and select the corresponding cities based on the cumulative total.

The selected numbers are:

• 10: This corresponds to the first store in city 1.
• 60: This corresponds to the second store in city 5.
• 110: This corresponds to the third store in city 3.
• 160: This corresponds to the fourth store in city 7.
• 210: This corresponds to the fifth store in city 9.
• 260: This corresponds to the sixth store in city 10.
• 310: This corresponds to the seventh store in city 11.
• 360: This corresponds to the eighth store in city 12.
• 410: This corresponds to the ninth store in city 13.
• 460: This corresponds to the tenth store in city 14.
 So, we have selected:
•1 store from city 1 (35 stores).
•1 store from city 3 (10 stores).
•1 store from city 7 (26 stores).
•1 store from city 9 (26 stores).
•1 store from city 10 (66 stores).
•1 store from city 11 (37 stores).
•1 store from city 12 (44 stores).
•1 store from city 13 (33 stores).
•1 store from city 14 (29 stores).
•2 stores from city 5 (70 stores).

Using proportional sampling based on size, the sample of 10 stores is selected as follows:
2 stores from city 5,1 store from each of the following cities: 1, 3, 7, 9, 10, 11, 12, 13, and 14.

This ensures that the number of stores selected from each city is proportional to the number
of stores in the city.