Sampling in Research

Sampling in Research
Research Methods: ALD4105

Syed S. Hossain, University of Dhaka

Syed S. Hossain, University of Dhaka

Sampling in Research

Probability Sampling Methods

A sampling method that gives each unit in the population a known,

non-zero chance of being selected is called a probability sampling method.
In the analysis of the sample, weights appropriate to the probabilities are
utilized to increase validity of the findings. The most commonly used and
most familiar methods are:
Simple Random Sampling
Stratified Random Sampling
Systematic Sampling
Cluster Sampling or Area Sampling
Multistage Sampling

Syed S. Hossain, University of Dhaka

Sampling in Research

Simple random sampling (SRS)

A simple random sample of size n is a sample of n units selected in

such a way that every possible sample of the given size has the same
chance of being selected. Samples of different sizes may have
different chances of being selected.
The SRS method can be
with replacement (WR)
without replacement (WOR).

Syed S. Hossain, University of Dhaka

Sampling in Research

Selection Procedure

To obtain a simple random sample of size n using a table of random

numbers,
1 Assign every element in the population a number, beginning with 1
and ending with N.
2 Go to the table and ”randomly” select a starting point.
3 Record the numbers as they are read from the table; one records as
many digits as there are digits in N (e.g., if N is 79, record two-digit
numbers), but disregard any numbers chosen that exceed the value of
N.
When the sample is selected in this manner, every element in the
population has an equal chance of selection, and every combination of n
elements has an equal chance; i.e., a simple random sample is obtained.

Syed S. Hossain, University of Dhaka

Sampling in Research

Features of SRS

Good for This sampling will give good sample (better representation)
if the population of interest is homogeneous with respect to the
characteristic of the interest.
Not good for The situations when SRS is not a good option are:
When the units of the population are heterogeneous with respect to
the characteristics of study
As every unit has equal chance of selection, in a large survey the units
selected may be widely scattered posing great operational difficulty and
thus incurring high cost.
Preparation of the frame (list of units for sampling) for a large
population may be impossible or at least not easy, time consuming and
cost-wise prohibitive.

Syed S. Hossain, University of Dhaka

Sampling in Research

Example 1

The following are the age data of 36 patients in an hospital:

52 28 45 25 28 25 65 58 31
70 22 25 62 47 25 35 29 23
45 25 32 15 75 42 53 30 30
36 75 52 17 27 40 35 30 11
Describe the method for drawing a sample size of 10 using the simple
random sampling.

Syed S. Hossain, University of Dhaka

Sampling in Research

Results related to SRS

An unbiased estimator of the population mean Ȳ is given by the

sample mean
1X
ȳ = yi .
n u ∈s
i

The variance of ȳ is given by

N
1 2 1 X
V (ȳ ) = σ (Y) = (yi − Ȳ )2 , for WR SRS,
n nN
i=1

N
N −n X
V (ȳ ) = (yi − Ȳ )2 , for WOR SRS.
nN(N − 1)
i=1

Syed S. Hossain, University of Dhaka

Sampling in Research

Results related to SRS (cont.)

An estimate of the variance of ȳ is given by

1 X (yi − ȳ )2
v (ȳ ) = , for WR SRS ,
n u ∈s n − 1
i

N − n X (yi − ȳ )2
v (ȳ ) = , for WOR SRS.
nN u ∈s n − 1
i

Note: It can easily be observed that the variance and estimated

variances are both inversely related with the sample size n

Syed S. Hossain, University of Dhaka

Sampling in Research

Relative Precision

Comparisons between two different sampling methods are usually

made on the basis of relative precision (RP). The following Table
illustrates the idea of RP:
Method Estimator Variance of Raltive precision
the estimator
1/V (θ̂B ) V (θ̂A )
A θ̂A V (θ̂A ) 1/V (θ̂A )
= V (θ̂B )
B θ̂B V (θ̂B )
Often V (θ̂A ) and V (θ̂B ) are found to be inversely related function of
sample size.
Note: If the method B is SRS, then the relative precision is often
known as design effect (deff ).

Syed S. Hossain, University of Dhaka

Sampling in Research

Systematic random sampling

For a 1-in-k systematic sample, you order the units of the population in
some way, and randomly select one of the first k units in the ordered list.
This selected unit is the first unit to be included in the sample. You
continue through the list selecting every k t h unit from then on.
Advantages The advantages of the systematic sampling are:
Sample is easy and fast to select.
Sample is evenly spread over the entire reference population.
Sampling is possible also in situations where frame is not possible to be
constructed for example in case of a hospital out-door clinic. In this
situation we find a suitable sampling interval and select patients/people
accordingly.
Disadvantages If the frame or the sampling units has some hidden
periodicity, which coincides with selections the results will be biased.

Syed S. Hossain, University of Dhaka

Sampling in Research

Sampling Procedure

Suppose we want to select a sample of size 20 from a population of

200.
We first find the sampling interval by dividing N = 200 by n = 20 i.e.
Sampling Interval = Nn = 200
20 = 10.
select a number at random which may be any number between 1 and
k
select a number at random which may be any number between 1 and
10. Suppose 3 is selected. So item number 3 in the frame is our first
unit. The second unit will be 3 + 10=13th unit. Thus the series of
20 items that will be selected are: 3, 13, 23, . . . , 193.

Syed S. Hossain, University of Dhaka

Sampling in Research

Stratified random sampling

The population under study is first divided into homogenous groups or

classes called strata. Sampling is carried out in each stratum following
exactly the simple random sampling procedure.
Good for It gives a better representation of population for a
heterogeneous population. As a result, the variation of estimates from
sample to sample i.e., sampling variation is minimized and precession
increased.
Not Necessary for It is not necessary for a homogeneous population
because it encurs more complexity of stratifying than SRS, which was
not needed.

Syed S. Hossain, University of Dhaka

Sampling in Research

Sampling Procedure

In this procedure of sampling, selection is done according to the following

steps
Define the population
Identify the strata
Determine the sub-sample sizes
Select items within each stratum by SRS.

Syed S. Hossain, University of Dhaka

Sampling in Research

Allocation of samples among the strata

In stratified random sampling, the units in population will be divided into

L sub-populations of N1 , N2 , ..., NL units. And n1 , n2 , ..., nL units of SRS
from these strata comprise the total sample size n. The sample sizes in
different strata can be allocated in one of the different principles.
Equal allocation: In this allocation the sample size is allocated as
nh = Nn , i.e. the sample size from each stratum will be equal
irrespective of the size of the stratum in the population.
Proportional allocation: In this allocation the sample size is allocated
by satisfying the condition Nnhh = Nn . That is, if the elements of a
stratum comprise (for example) the 15% of the population then the
15% of the selected sample should also come from that stratum.

Syed S. Hossain, University of Dhaka

Sampling in Research

Allocation of samples among the strata

Neyman Allocation: To account for larger sample from higher
heterogenity, in this allocation the sample size is allocated by
satisfying the condition that nh is proportional to Nh Sh , where Sh is
the standard deviation in the hth stratum. i.e.,
Nh Sh
nh = n × PL .
h=1 Nh Sh

Optimum allocation: When cost of survey vary over strata, an

allocation can be made to optimise the variability for minimum cost.
In this case the sample size is allocated by satisfying the condition
that nh is proportional to N√hCSh , where Ch is the per unit cost in the
h
hth stratum. i.e.,
N
√h Sh
Ch
nh = n × PL Nh Sh ,
√
h=1 Ch
Syed S. Hossain, University of Dhaka
Sampling in Research

Cluster sampling

In cluster sampling, the units of the population are grouped into cluster.
One or more clusters are selected at random. If a cluster is selected, all of
the units that form that cluster are included in the sample.
Good for IIt gives a better representation of population for a
heterogeneous population. As a result, the variation of estimates from
sample to sample i.e., sampling variation is minimized and precession
increased.
Not Necessary for It is not necessary for a homogeneous population
because it encurs more complexity of stratifying than SRS, which was
not needed.

Syed S. Hossain, University of Dhaka

Sampling in Research

Sampling Procedure

In this procedure of sampling, selection is done according to the following

steps
Define the population.
Verify that elements in each cluster are similar to elements in other
clusters
A sample of such clusters is then selected.
All the units in the selected clusters are then examined or studied.

Syed S. Hossain, University of Dhaka

Sampling in Research

Multistage sampling

In some cases of sampling the sample may be selected in stages according

to specified method at different stages. This type of sampling is termed as
multistage sampling.
Good for It saves cost and time a perform as good as SRS if the units
within cluster are homogenous and between clusters are heterogenous.
Not Good for If the units are heterogenous within cluster, this method
may give misleading results.

Syed S. Hossain, University of Dhaka

Sampling in Research

Sampling Procedure

In this procedure of sampling, selection is done according to the following

steps
The population is first divided into a number of large clusters called
primary sampling units (PSU),
Primary sampling units are again divided into smaller cluster called
second stage units (SSU),
The process is continued until the last stage (say kth stage) which
the units are the elements for which the data are collected,
At every stages, a number of cluster are selected within the selected
clusters of previous stage.
Remember that smaller the number of stages get better results of the
estimates.

Syed S. Hossain, University of Dhaka

Sampling in Research

Non-probability sampling

can’t use probability theory

Accidental,
haphazard or
convenience sampling-
Eg.
man on the street or
person who volunteers

Syed S. Hossain, University of Dhaka

Sampling in Research

Different non-probability sampling

Purposive sampling- sampling with a purpose in mind

Quota sampling- sampling until a pre-assigned quota is filled
Inverse sampling- Number of objects in a category pre-specified,
sample size variable
Non-proportional sampling - minimum number in each category
Heterogeneity sampling- want a range of response and don’t worry
about sample size
Snowball sampling- start with one who meets criteria and as to
recommend other ,

Syed S. Hossain, University of Dhaka