SAMPLING TECHNIQUES

SAMPLING
• Sampling may be defined as the selection of some
part of an aggregate or totality on the basis of which
a judgement or inference about the aggregate or
totality is made.
• is the process of obtaining information about an
entire population by examining only a part of it.
• In most of the research work and surveys, the usual
approach happens to be to make generalizations or
to draw inferences based on samples about the
parameters of population from which the samples
are taken.
 Sampling Terms and Procedures

•Population - inclusive group defined by researcher

•Sample - representative subset of population
❖should contain essential elements of population
❖Samples are only estimates
❖The difference between the sample estimate and the
true population is the “sampling error.”
 SAMPLING TECHNIQUES
The Need for Sampling
If a researcher desires to obtain information about a population
through questioning or testing, he/she has two basic options:
1. Every member of the population can be questioned or tested,
a census; or
2. Only selected members of the population are questioned or
tested, a sample.
 Why sampling is required?
We cannot examine the whole population because of:
• The large size the population

Example:
• Time constraint: suppose if we have currently 10000
boxes, and each box requires approximately 1 minute to
examine, that means we need a total of 10000 minutes to
examine all the boxes.
 Cont…
• Inaccessibility of some of the population -
Some populations are so difficult to get access
to that only a sample can be used.
• Example
prisoners, people with severe mental illness,
disaster survivors etc. The inaccessibility may be
associated with cost or time or just access.
 Cont….
• Destructiveness of the observation- Sometimes the very act of
observing the desired characteristic of the product destroys it for the
intended use.

Example

to determine the quality of a fuse and whether it is defective, it must

be destroyed. Therefore if you test all the fuses, all would be
destroyed.

• Accuracy and sampling - A sample may be more accurate than the

total study population. A badly identified population can provide less
reliable information than a carefully obtained sample
 Characteristics of Good Sampling Design

 REPRESENTATIVENESS: A sample is a subset of the

population or universe. The sample must be representative of the

universe. Therefore, the researcher must select the sample

members who have the characteristics of the universe.

 FOCUS ON OBJECTIVES: The sample size must be selected

depending upon the research objectives.

 Cont…
 FLEXIBILITY: The sample size should not be
rigidly followed. It can be modified depending
upon the circumstances.

For instance, the sample size may be reduced, if

sufficient information is already available or if
there is a limitation of time and funds. However,
sample size may be increased, if proper information
is not available from the current sample.
 Cont…
• METHOD OF SAMPLING: The researcher
must select proper method of sampling. The
sampling methods are broadly divided into two
groups; probability method and non-
probability methods. Certain methods require
less time to complete data collection.
 Cont…
✓the researcher may select convenience method, if
there are limitations of time.

❑PROPER SELECTION OF SAMPLE UNIT:

✓ The sample unit must be appropriate. The

universe comprises of the elements, and each
element can be further divided into units
 Cont…
❑PROPER SAMPLING FRAME:

• sampling frame is an instrument to obtain

addresses or such other information about
various element of the universe. The sampling
frame may include telephone directories, register
of member in an organization, etc.
 Cont…

• Before selection of sampling frame, the

researcher must answer the following questions:

✓Does it adequately cover the universe?

✓Does it represent each and every unit?

✓Is the sample frame up-dated?

 Cont…
 PROPER SAMPLING PLAN: the researcher must prepare a
sampling plan, which must indicate:
• Sampling unit
• Sampling frame
• Sources of data
• Methods of data collection
• Resources required for data collection
• Time frame to collect data, etc
 Cont…

• GEOGRAPHIC AREA OF THE STUDY:

the researcher must consider the size of the

area for selecting the sample size

• SUITABILITY: sample size should be suitable

to collect the relevant data.
 Cont…
• ECONOMY:

✓the sample size must be economical

✓The sample size must be cost-effective

✓it should not put extra burden on the resources

✓ it facilitates proper collection of data

 Types of Sampling
❖ Probability or Random sampling
❖ Non probability or Non random sampling.

Probability or Random sampling

▪ Provides a known non-zero chance of selection
for each population element
▪ It is used when generalization is the objective of
study, and greater degree of accuracy of
estimation of population is required.
 Types of Probability Sampling
▪ Simple Random Sampling

▪ Stratified Random Sampling

▪ Systematic Random Sampling

▪ Cluster random Sampling

❖ Simple Random Sampling

➢ This sampling technique gives each element an

equal independent chance of being selected.
 Cont…
Example: Selecting 10 students out of 43 Construction
Management PG students

Suitability: This type of sampling is suited for a

small homogeneous population.
The procedure of drawing a simple random sample
consists of enumeration of all elements in the population

1. Preparation of a list of all elements, giving them

numbers in serial order 1,2,3 and so on and
2. Drawing sample numbers by using
➢ Lottery method
➢ A table of random numbers
➢ Computer
 Stratified Random Sampling
In this method the population is sub-divided into
homogeneous groups or strata and from each stratum,
random sample is drawn.
Example: University students can be divided on the basis
of discipline, and each discipline group may again be
divided into junior and senior.
Stratified random sampling can be classified into:
❖ Proportionate stratified random sampling and
❖ Disproportionate stratified random sampling
❖ Proportionate stratified random sampling

• This sampling involves drawing a sample from each

stratum in proportion to the latter’s share in the total
population.

• Gives proper representation to each stratum and its

statistical efficiency is generally higher.
❖ Disproportionate stratified random sampling

• Does not give proportionate representation to strata.

• Involves over-representation to some strata and under
representation to some strata.

Suitability:- This method is used when:

❖ the population contains some small but important subgroups

❖ certain groups are quite heterogeneous, while others are

homogeneous

❖ it is expected that there will be appreciable differences in the

response rates of the groups in the population.
 Systematic Random Sampling
• This method of sampling is an alternative to random

selection.

• It consists of the kth item in the population after a

random start with an item from 1 to k.

• It is also known as fixed interval method. E.g. 1st , 11th ,

21st , etc.
 Cluster random Sampling
• Population is divided into groups, usually geographic or
organizational

• Some of the groups are randomly chosen

• In pure cluster sampling, whole cluster is sampled.

• In simple multistage cluster, there is random sampling

within each randomly chosen cluster

Non probability or Non random sampling.
• Is not based on the theory of probability.
• Doesn’t provide a chance of selection to each population
element.

Advantages: The only merits of this type of sampling are

simplicity, convenience and low cost.

Disadvantages:
• It does not ensure a selection chance to each population
unit.
• I t offers sampling bias which will distort results.
 Reasons for usage of Non random sampling
• when there is no other feasible alternative due to non-
availability of a list of population.
• when the study does not aim at generalizing the findings to
the population.
• when the costs required for probability sampling may be
too large
• when probability sampling requires more time, but the time
constraints and the time limit for completing the study do
not merit it.
 Types of Non Probability Sampling

❖ Convenience or Accidental Sampling

❖ Purposive ( Judgment) Sampling

❖ Quota Sampling

❖ Snowball Sampling
 ❖ Convenience or Accidental Sampling

➢ It is selecting samples which are conveniently available

E.g. A teacher may select students in his class

Suitability: Though this type of sampling has no status,

it may be used for simple purposes such as testing ideas
or gaining ideas or a rough impression about a subject of
interest.
 Advantage of Convenience or Accidental Sampling
▪ It is the cheapest and simplest

▪ It does not require a list of population and it does not

require any statistical expertise.

Disadvantage:

▪ It is highly biased because of researcher’s subjectivity

▪ It is the least reliable sampling method and the

findings can not be generalized.
 ❖ Purposive ( Judgment) Sampling

• is a deliberate selection of sample units that conform to

some pre-determined criteria.

• It involves selection of cases which we judge as the

most appropriate ones for the given study.

• It is based on the judgment of the researcher or some

expert.
Suitability:
It is used when what is important is the typicality and

specific relevance of the sampling units to the study and

not their overall representativeness to the population.

Advantage: It is less costly and more convenient and

guarantees inclusion of relevant elements in the sample.
Disadvantages:

• It is less efficient for generalization.

• Does not ensure the representativeness

• Requires more prior extensive information and does

not lend itself for using inferential statistics.

❖ Quota Sampling
It is used when:
❖ the population has different strata.
❖ stratified random sampling is impractical

In quota sampling, interviewers (researchers) may fix

certain numbers to the subgroups to be sampled.

Example: 100 male and 100 female
 ❖ Snowball Sampling
✓ is a recruitment technique in which research participants
are asked to assist researchers in identifying other
potential subjects.

✓ the researcher asks participants to identify other

participants to become members of the sample.

✓ used when the samples have traits that are rare to find.
 Sampling error and Sampling Bias

Errors and bias may arise if the coverage,

valuation, and choice of the sampling unit fail to
meet a conceptual need.
 Sampling Error

• Sampling error comprises the differences

between the sample and the population that are

appropriate only to the particular participants that

have been selected.

 Classification of Errors

Are of two kinds :

• sampling error (“random error”)and

• non-sampling error (“systematic error”)

 Con…
• Sampling error results from the luck of the draw

when choosing a sample: we get a few too many units of

one kind, and not enough of another.

• A non sampling error is an error that results solely

from the manner in which the observations are made.

 Con…

Non-sampling error itself can be broken down into three

main categories.

1. selection bias,

2. non-response bias, and

3. response bias.
 Con…

1. “Selection bias” is a systematic tendency to

exclude one kind of unit or another from the sample.
2. Non-response bias- the people who hang or who
are not willing to be interviewed.
3. Response bias- Respondents can easily be lead to
shade the truth, by interviewer attitudes, the
precise wording of questions, or even the
juxtaposition of one question with another
 The main cause of sampling error

Chance: That is the error that occurs just because of

bad luck

Sampling bias: is usually the result of a poor

sampling plan.
 Non-sampling error (measurement error)

is inaccurate measurements due to malfunctioning

instruments or poor procedures.

• The interviewers effect: The manner in which a question is

formulated can also result in inaccurate responses.

• The respondent effect : Participants may deliberately give

incorrect answers

• Knowing the study purpose - Knowing why a study is being

conducted may create incorrect responses
 Sampling Bias
Bias is a systematic error that can prejudice (unfairness)
your evaluation findings in some way. So, sampling bias
is consistent (steady) error that arises due to the sample
selection

. For example a survey of high school students to measure

teenage use of illegal drugs will be a biased sample
because it does not include home schooled students or
dropouts
 Sample Size Determination
• How large a sample should be?

(There is no clear-cut answer.)

• Before deciding how large a sample should

be, you have to define your study population
(who you are including and excluding in your
study).
 Sample size determination depends up on

• The type of data analysis to be performed

• The desired precision of the estimates one wishes to achieve
• The kind and number of comparisons that will be made
• The number of variables that have to be examined
simultaneously
• How heterogeneous the sampled population is.
• The available time and resources.
• The available funding
 How to determine a sample size
There are 5 steps in deciding a sample size.

1. Determine Goals
2. Determine desired Precision of results
3. Determine Confidence level
4. Estimate the degree of Variability
5. Estimate the Response Rate
 Step One: Determine Goals

• First, know the size of the population with which you’re dealing.
If your population is small (200 people or less), it may be
preferable to do a census of everyone in the population, rather
than a sample.

• Second, decide the methods and design of the samples

• Third, know what kind of resources you have available

Step Two: Determine the Desired Precision of Results

• The level of precision is the closeness with which

the sample predicts where the true values in the
population lie.

• High levels of precision require larger sample sizes

and higher costs to achieve those samples,
Step Three: Determine the Confidence Level
• The confidence level involves the risk you’re willing to
accept that your sample is within the average

Step Four: Estimate the Degree of Variability

• Variability is the degree to which the attributes or

concepts being measured in the questions are distributed
throughout the population
 Con…

• Note: when the population is extremely

heterogeneous a larger sample may be needed for
an accurate result
 Step Five: Estimate the Response Rate

• The base sample size is the number of responses you

must get back when you conduct your survey.

• To estimate response rate that you are likely to get,

you should take into consideration the method of your
survey and the population involved
An equation for determining final
sample size
 Where:
n= sample size required
N= number of people in the population
P= estimated variance in population, as a decimal
(0.5 for 50-50, 0.3 for 70-30)
A= precision desired, expressed as a decimal(i.e 0.03, 0.05,
0.1 for 3%, 5%, 10%)
Z= based on confidence level: 1.96 for 95%confidence,
1.6449 for 90% & 2.5758 for 99%
R= Estimated response rate as a decimal
 CONCLUSION
• Using a sample in research saves money and time,

• If a suitable sampling strategy is used, appropriate

sample size selected and necessary precautions taken to

reduce on sampling and measurement errors, then a

sample should yield valid and reliable information.