Sampling techniques

Two broad divisions:

A. Probability sampling methods

B. Non-probability sampling

methods
Random sampling techniques:-
§ provides a scientific techniques of drawing samples from
the population according to some laws of chance in
which each element in the population has some
definite pre-assigned probability being selected in the
sample.
§ Probability sampling is:
– more complex,
– more time-consuming and
– usually more costly than non-probability
sampling.
§ However, because study samples are randomly
selected and their probability of inclusion can be
calculated,
– reliable estimates can be produced and
– inferences can be made about the population.
Sampling techniques (Cont.)
Simple random sampling:- is a random
sampling technique that selects samples
by the method that allow each item in
the population to have an equal chance
of being included in the sample and each
possible sample to have equal probability
of being selected.
ü Lottery Method
ü Use of random number table

§ This is the most basic scheme of random sampling.

Sampling techniques (Cont.)
2. Systematic random sampling:- only the first
sample item is selected at random and the
remaining items are automatically selected
in a definite sequence at equal spacing from
one another.

It requires the sampling units in the

population have to be ordered in such a way
that each item in the population is uniquely
identified by its order, alphabetically,
chronologically. etc
♦ Individuals are chosen at regular intervals (for example, every
kth) from the sampling frame.

♦ The first unit to be selected is taken at random from among the

first k units.

♦ For example, a systematic sample is to be selected from 1200

patients of a hospital. The sample size is decided to be 100.

♦ The sampling fraction is: 100 /1200 = 1/12.

♦ Hence, the sample interval is 12.

♦ The number of the first patient to be included in the sample is
chosen randomly, for example by blindly picking one out of
twelve pieces of paper, numbered 1 to 12.

♦ If number 6 is picked, every twelfth patient will be included in

the sample, starting with student number 6, until 100 patients
are selected.

♦ The numbers selected would be 6,18,30,42,etc

Merits

♦ Systematic sampling is usually less time consuming and easier to perform

than simple random sampling.

It provides a good approximation to SRS.

Demerits

♦ If there is any sort of cyclic pattern in the ordering of the subjects which
coincides with the sampling interval, the sample will not be representative of
the population.

Examples

- List of married couples arranged with men's names alternatively with the
women's names (every 2nd, 4th, etc.) will result in a sample of all men or
women).
Sampling techniques (Cont.)
3. Stratified random sampling:- it is used when the population is
heterogeneous (or non-uniform) with respect to the
characteristics under study. In this case divide the population
into relatively homogenous subgroups called strata, such that
ü The elements within each stratum are homogenous as possible.
ü The difference between various strata are as marked as
possible.
ü Each and every element in the population belong to one and
only one stratum.
♦ The population is first divided into groups (strata) according
to a characteristic of interest (eg., sex, geographic area,
prevalence of disease, etc.).

♦ A separate sample is then taken independently from each

stratum, by simple random or systematic sampling.
Sampling techniques (Cont.)
♦
Merit

♦ The representativeness of the sample is improved.

♦ That is, adequate representation of minority subgroups of

interest can be ensured by stratification and by varying the
sampling fraction between strata as required.

Demerit

♦ Sampling frame for the entire population has to be prepared

separately for each stratum.
Sampling techniques (Cont.)
4. Cluster random sampling :-it is used when
the population is uniform with respect to the
characteristics under study. In this case
divide the population into some recognizable
subgroups called clusters, such that
üThe elements within each cluster are non-
homogenous as possible.
üThe difference between various clusters is not
significant.
üEach and every element in the population
belong to one and only one cluster.
Sampling techniques (Cont.)
♦ Finally take a simple random sampling on the
clusters.

♦ The clusters selected with each element in it

will constitute the required sample. The
reference population (homogeneous) is
divided into clusters.

♦ These clusters are often geographic units (eg

districts, villages, etc.)
Merit
♦ A list of all the individual study units in the reference population is
not required.
♦ It is sufficient to have a list of clusters.
Demerit
♦ It is based on the assumption that the characteristic to be studied is
uniformly distributed throughout the reference population, which may
not always be the case.
♦ Hence, sampling error is usually higher than for a simple random
sample of the same size.
 II. Non-probability sampling

v No random selection (unrepresentative of the given population)

v Used when a sampling frame does not exist

v Inappropriate if the aim is to measure variables and generalize

findings obtained from a sample to the population.

v They are cheaper and easier.

v Good for pretests, pilot studies, In-depth interviews

Sampling techniques (Cont.)
♦ Non-random sampling procedures should
never be used when the objective of
sampling exercise is inference.

♦ Thus non-random sampling should be

used only if we are willing to restrict our
study to descriptive statement about the
sample and forge (give up) inferential
statements about the population.
Sampling techniques (Cont.)

1. Convenience sampling:-selecting a sample

where it is suitable for your purpose is the
primary consideration.

2. Judgment sampling:- selecting a sample

based on prior experiences with the
population of interest. Personal knowledge
and opinion are used to identify those item
from the population that are to be included in
the sample.
 Volunteer sampling
♦ As the term implies, this type of sampling
occurs when people volunteer to be involved
in the study.
♦ In pharmaceutical trials (drug testing), for
example, it would be difficult and unethical
to enlist random participants from the
general public.
♦ In these instances, the sample is taken from
a group of volunteers.
♦ Sometimes, the researcher offers payment
to attract respondents.

♦ In exchange, the volunteers accept the

possibility of a lengthy, demanding or
sometimes unpleasant process.
 Quota: selection of samples based on a fixed quota.
vInvestigator interviews as many people as he can find
until he has filled his quota.
sampling distribution
♦ Researchers often use sample survey methodology to
obtain information about a larger population by selecting
and measuring a sample from that population.

♦ Since population is too large, we rely on the information

collected from the sample.
♦ However, due to the variability in the
characteristics of the population, scientific sample
designs should be applied to select a
representative sample.
♦ If not, there is a high risk of distorting the view of the
population
♦
♦ Sample: A sample from a population is the set of
measurements that are actually collected in the course of an
investigation. It should be selected using some pre-defined
sampling technique in such a way that they represent the
population very well.
♦ Sampling enables us to estimate the characteristic of a
population by directly observing a portion of the population.
♦ Researchers are not interested in the sample itself, but in
what can be learned from the sample—and how this
information can be applied to the entire population.
§ Therefore, it is essential that a sample
should be correctly defined and organized.

§ If the wrong questions are posed to the

wrong people, reliable information will not
be received and lead to a wrong conclusion
when applied to the entire population.
In drawing a sample, there
will be some challenges
§ What is the group of people
(population) from which we want to
draw a sample?
§ How many people do we need in our
sample?
§ How will these people be selected?
 Common Terms Used in Sampling
§ Reference/source or target population):-
the population of interest, to which the
investigators would like to generalize the results
of the study.
§ Study population:- the population from which
we actually select samples.
§ Sampling unit:- the unit of selection in the
sampling process.
example, in a sample of districts, the sampling
unit is a district; in a sample of households, the
household; etc.
§ Study unit:- the units on which information will be
collected, for example, persons, housing units, etc.
§ Sampling frame:- the list of the units in the
reference population, from which a sample is to be
drawn.
§ Sampling fraction (sampling interval):- the ratio
of the number of units in the sample to the number
of units in the sampling frame or reference
population.
Example, a sampling fraction or ratio of 1:4 is
equivalent to a sampling interval of 1 in every 4 units.
This means that the sample constitutes 25% of the
total units in the sampling frame or reference
population.
 Advantages of sampling:

♦ Feasibility: Sampling may be the only feasible

method of collecting information.
♦ Reduced cost: Sampling reduces demands on
resource such as finance, personnel, and material.
♦ Greater accuracy: Sampling may lead to better
accuracy of collecting data
♦ Greater speed: Data can be collected and
summarized more quickly
 Disadvantages of sampling:

♦ There is always a sampling error.

♦ Sampling may create a feeling of
discrimination within the population.
♦ Sampling may be inadvisable where every
unit in the population is legally required to
have a record.
 Errors in sampling
1) Sampling error: Errors introduced due to
the process of sampling.
§ Sample statistics are used to estimate
population parameters.
e.g. Sample mean(X) is an estimate of the
population mean, μ
Problems
-different samples provide different estimates.
-Sample results have potential variability, thus
sampling error exists.
 Calculating sampling error
§ It is the difference between a value
(statistics) computed from a sample and the
corresponding value (a parameter) computed
from the population.
Example (for the mean)
Sampling error = sample mean –
population mean
Note
Sampling error may be positive or negative
Sampling error decreases as sample size increases.
 Sampling Distribution

♦ Since the sample measurement vary from sample to sample, the

value of a statistic will vary from sample to sample.

♦ Therefore, to asses the reliability of an inference based on a statistic

computed from a sample values, we must be able to determine or

approximate the sample distribution of that statistic, which is a

probability distribution in repeated sampling.

 Sampling distribution (Cont.)
♦ The sampling distribution of a statistic is a
probability distribution of a statistic that results
when random samples of size n are repeatedly
drawn from a given population.
♦ Knowledge of sampling distribution of a statistic
allows us:
üTo choose the best from among the several
competing statistics available for estimating the
population parameter.
üTo determine the limit within which we could expect
the value of an estimator to lie with a specified
probability.
Sampling distribution of the mean
♦
 Sampling distribution of the mean (Cont.)
If we take a sample of size 3 drawn with out
replacement with equally likely probability, we
have 10 possible samples and the
corresponding sample mean are shown in the
following table:

Sample 3, 6, 3, 6, 3, 6, 3, 9, 3, 9, 3, 12 , 6, 9, 6, 9, 6, 9,12,
value 9 12 15 12 15 15 12 15 12, 15
15
Sample 6 7 8 8 9 10 9 10 11 12
mean
Sampling distribution of the mean (Cont.)

6 7 8 9 10 11 12
x
P (x ) 1
10
1
10
2
10
2 2
10
1
10
1
x 10 10
Sampling distribution of the mean (Cont.)

♦ The standard deviation of the sampling

distribution of the sample means (or the
standard error), denoted and given by:

 x   (x   x )2 P (xi )  3

and measures the extent to which

sample mean vary due to chance.
♦ From this example you can observe that:
ü  x   and  x  
Sampling distribution of the mean (Cont.)

♦
Sampling distribution of the mean (Cont.)

♦
Sampling distribution of the mean (Cont.)

♦ This means that, as the sample size

increases, the sampling distribution
of the sample mean remains centered
on the population mean,
♦ but becomes more compactly
distributed around that population
mean.
Sampling distribution of the mean (Cont.)
Example Suppose a population that is normally
distributed with mean equal to 106 and
standard deviation equal to 12, for the
associated random variable X.
a) Find the probability that X exceeds 110.
b) Suppose a random sample of observation is
selected from the population, find the
probability that the sample mean exceeds
110.

Exercise: For the above example find the

probability that the sample mean will deviate from
the population mean 106 by no more than 4.
 Sampling distribution of the mean (Cont.)

♦
Sampling distribution of the mean
(Cont.)
♦
Sampling distribution of the mean(Cont.)

n=5
0.25
0.20
0.15
0.10
0.05
0.00

0.2
n = 20
0.1

0.0

0.4
Large n
0.3
0.2
0.1
0.0


-
Sampling distribution of the mean (Cont.)
The Central Limit Theorem Applies to Sampling Distributions
from any Population
Normal Uniform Skewed General

Population

n=2

n = 30

 X  X  X  X
Sampling distribution of the proportion

♦
Sampling distribution of the proportion
(Cont.)
♦
Sampling distribution of the proportion
(Cont.)
♦