SAMPLING METHODS

Objective
After Completing this chapter the students is able to:

 Describe common terms used in sampling

 Differentiate between random error and bias

 Differentiate between probability and Non-Probability

sampling methods

 Apply different techniques of sampling

3
Introduction
 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.

 Inferences about the population are based on the

information from the sample drawn from that
population.
4
Introduction…
 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.

Sample Information

Population
5
Sampling
 The process of selecting a portion of the population to
represent the entire population.

 Sampling enables us to estimate the characteristic of a

population by directly observing a portion of the population.

 A main concern in sampling:

 Ensure that the sample represents the population
(representativeness)

The findings can be generalized (Generalizability).

6
Sampling…
 If we have to draw a sample, we will be confronted with the
following questions:

 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?

7
Advantages of Sampling…
❶ Feasibility: Sampling may be the only feasible method of
collecting information.

❷ Reduced cost: Sampling reduces demands on resource

such as finance, personnel, and material.

❸ Greater accuracy: Sampling may lead to better accuracy

of collecting data.

❹ Greater speed: Data can be collected and summarized

more quickly.
8
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.

9
Errors in Sampling
 When we take a sample, our results will not exactly equal
the correct results for the whole population.

 That is, our results will be subject to errors.

 They are two forms of error

❶. Sampling error

❷. Non-sampling error

10
Sampling Error or Random Error
 A sample is a subset of a population. Because of this
property of samples, results obtained from them cannot
reflect the full range of variation found in the population.

 This type of error, arising from the sampling process itself, is

called sampling error.

 Sampling error can be minimized by increasing the sample

size.

 When n = N ⇒ sampling error = 0

11
Non-Sampling Error (Bias)
 It is a type of systematic error in the design or conducts of
a sampling procedure which results in distortion of the
sample, So that it is no longer representative of the reference
population.

 We can eliminate or reduce the bias by careful design of the

sampling procedure and not by increasing the sample
size.
Non-sampling error: Observational error, respondent error,
lack of preciseness of definition 12
Common Terms in Sampling
 Reference population (or target population): the population
of interest to whom the researchers would like to make
generalizations.

 Sampling population: the subset of the target population

from which a sample will be drawn.

 Study population: the actual group in which the study is

conducted = Sample

 Study unit: the units on which information will be collected:

13
persons, housing units, etc.
Common Terms in Sampling……
 Researchers are interested to determine the magnitude of breast
self examination practice among school going adolescent girls in
Harar town.
Target population =
All school going adolescent girls
in the town.

Sampling population =
All school going adolescent girls
in selected schools of the town
e.g. 6 schools in the town.

Sample 14
Common Terms in Sampling…
 Sampling unit: subject under observation on which
information is collected.

 Sampling fraction: ratio between the sample size and the

population size.

 Sampling frame: list of all the sampling units in the

population from which a sample is to be picked.

 Sampling scheme (Design): method of selecting sampling

units from sampling frame.
15
Sampling Scheme (Design)
 There are two categories of sampling methods:

❶. Non-probability sampling methods

❷. Probability sampling methods

16
Non-Probability sampling
methods
Non-Probability Sampling Methods
 A type of sampling where each study unit in the population
has an unknown probability of inclusion in the sample.

 The selection of subjects is arbitrary or subjective.

 In this sampling, there is an assumption that there is an even

distribution of a characteristic of interest within the
population.

18
 Advantages of Non-probability
Sampling Methods
 Useful when descriptive comments about the sample itself
are desired.
 Used when a sampling frame does not exist.
 They are quick, inexpensive and convenient.
 Used when Precise representativeness is not necessary
 Used when difficult or impossible to obtain the list of
names for sampling (Homeless, IV Drug user).
 When it is unfeasible or impractical to conduct
probability sampling (e.g. Animal studies). 19
 Disadvantages of Non-probability
Sampling Methods
 No random selection (unrepresentative).

 Reliability cannot be measured.

 No way to measure the precision of the resulting sample.

 Inappropriate for generalizing findings.

20
Types of Non-Probability Sampling
 The most common types of non-probability sampling are:

❶. Convenience or haphazard sampling

❷. Volunteer sampling

❸. Judgment sampling

❹. Quota sampling

❺. Snowball sampling technique

21
Convenience Sampling
 Convenience sampling can be referred as haphazard or
accidental sampling.

 Convenience sampling is a method in which for convenience

sake the study units that happen to be available at the time
of data collection are selected.

 The sample is not representative of the target population

because sample units are only selected if they can be
accessed easily and conveniently.
22
Convenience Sampling…
 The obvious advantage is that

 It is easy to use, but that advantage is greatly offset by

the presence of bias.

 Although useful applications of the technique are limited, it

can deliver accurate results when the population is
homogeneous.

23
Volunteer Sampling
 Volunteer/self selection: as the term implies, this type of
sampling occurs when people volunteer to be involved in
the study.
 Commonly applied when it would be difficult and unethical
to enlist random participants from the general public.
 Example: trials demanding long duration like in psychological
experiments or pharmaceutical trials (drug testing)

 In these instances, the sample is taken from a group of

volunteers.
24
Purposive/Judgment sampling
 This approach is used when a sample is taken based on
certain judgments about the overall population.

 The underlying assumption is that the investigator will

select units that are characteristic of the population.

 The researchers choose the sample based on who they think

would be appropriate for the study.

 Primarily used when there is a limited number of people

that have expertise in the area being researched.
25
Purposive/Judgment sampling…
 Researchers often use this method in exploratory studies
like pre-testing of questionnaires and focus groups.

 They also prefer to use this method in laboratory settings

where the choice of experimental subjects (i.e., animal,
human) reflects the investigator's pre-existing beliefs about
the population.

 One advantage of judgment sampling is the reduced cost

and time involved in acquiring the sample.
26
Quota Sampling
 Quota sampling is one of the most common forms of non-
probability sampling in which the population is first
segmented in to mutually exclusive sub-groups

 Sampling is done until a specific number of units (quotas)

for various sub-populations have been selected.

 Since there are no rules as to how these quotas are to be

filled, quota sampling is really a means for satisfying sample
size objectives for certain sub-populations.
27
Quota Sampling…
 As with all other non-probability sampling methods, in order
to make inferences about the population, it is necessary to
assume that persons selected are similar to those not
selected.

 The main argument against quota sampling is that it does not

meet the basic requirement of randomness.

 Some units may have no chance of selection or the chance of

selection may be unknown.
28
Snowball Sampling
 A technique for selecting a research sample where existing
study subjects recruit future subjects from among their
acquaintances.
 Involves a process of “chain referrals”
 Thus the sample group appears to grow like a rolling
snowball.
 This sampling technique is often used in hidden
populations or hard to reach groups which are difficult for
researchers to access. 29
Snowball Sampling…
 This sampling technique is often used in hidden
populations which are difficult for researchers to access;
example populations would be drug users or commercial
sex workers.

 Because 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.

30
Probability sampling
methods
Probability Sampling Methods
 A probability sampling: selection of a sample from a
population, based on the principle of randomization or
chance.

 All units of the population should have an equal or at least

a known & non-zero chance of being included in the
sample.

 Probability sampling is more complex, time-consuming

and costly than non-probability sampling.
32
Probability Sampling Methods…
 Since samples are randomly selected and their probability of
inclusion can be calculated, inferences can be made about
the population.

 There are several different ways in which a probability

sample can be selected. The method chosen depends on:
 The available sampling frame,

 How spread out the population is,

 How costly it is to survey members of the population

33
Types of Probability Sampling
 Most common probability sampling methods

1. Simple random sampling

2. Systematic random sampling

3. Stratified random sampling

4. Cluster sampling

5. Multi-stage sampling

34
Simple Random Sampling
 This is the most basic scheme of random sampling.

 The required number of individuals are selected at random

from the sampling frame, a list or a database of all
individuals in the population

 Each unit in the sampling frame has an equal chance of

being selected.

 Representativeness of the sample is ensured.

35
Simple Random Sampling…
To use a SRS method:

 Make a numbered list of all the units in the population

 Each unit should be numbered from 1 to N

 Decide on the size of the sample

 Select the required number of study units, using random

methods like:
 Use of “lottery’ methods
 Table of random numbers
 Computer programs 36
Simple Random Sampling…
 Random number table is a table of random numbers
constructed by a process that in any position in the table,
each of the numbers 0 through 9 has a probability 1/10 of
occurring.
…. 8094 2525 8247 1347 7433 3620 1897 ….
…. 3563 2198 8211 9045 2618 2751 2627 ….
…. 1330 6331 3753 9693 8738 6815 1538 ….
…. 3565 0016 2243 6432 4796 6095 5283 ….
…. 7850 5925 5588 7311 2192 4545 3530 ….
…. 4490 5417 9727 6153 5901 4878 9980 …. 37
Merits and Demerits of SRS
Merits
 Each unit in the sampling frame has an equal chance of being
selected.
 It does not require additional information on the frame.
 Easy to apply to small populations.
Demerits
 Can be an expensive and unfeasible for large dispersed
populations.
 Requires a sampling frame.
38
 Minority subgroups may not be selected.
Systematic Random Sampling
 Sometimes called interval sampling.
 Selection of individuals from the sampling frame
systematically rather than randomly.
 Individuals are taken at regular intervals down the list.
 The starting point is chosen at random.
 Important if the reference population is arranged in some
order:
 Order of registration of patients
 Numerical number of house numbers
 Student’s registration books 39
Steps in Systematic Random Sampling

1. Number the units on your frame from 1 to N (where N

is the total population size).
2. Determine the sampling interval (K) by dividing the
number of units in the population by the desired sample
size.
3. Select a number between one and K at random. This
number is called the random start and would be the first
number included in your sample.
4. Select every Kth unit after that first number. 40
Example
 To select a sample of 100 from a population of 400, you would
need a sampling interval of 400 ÷ 100 = 4. Therefore, K = 4.
 You will need to select one unit out of every four units to end up
with a total of 100 units
 Select a number between 1 and 4 from a table of random numbers.
 If you choose 3, the third unit on your frame would be the first unit
included in your sample;
 The sample might consist of the following units to make up a sample
of 100: 3 (the random start), 7, 11, 15, 19...395, 399 (up to N,
which is 400 in this case). 41
Merits and Demerits of Systematic Sampling

Merits
 Systematic sampling is usually less time consuming and easier to
perform than simple random sampling.
 Unlike SRS, systematic sampling can be conducted without a
sampling frame.
 E.g. In patients attending a health center, where it is not possible to
predict in advance who will be attending.
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
42
representative of the population.
Stratified Random Sampling
 It is done when the population is known to be have
heterogeneity with regard to some factors & those factors are
used for stratification.
 The population is first divided into homogeneous non
overlapping mutually exclusive groups (strata) according to
a characteristic of interest (e.g. Age, sex, geographic area,
prevalence of disease, etc.)
 There should be homogeneity within stratum and
heterogeneity between strata.
43
Stratified Random Sampling…
 Stratified sampling ensures an adequate sample size for
sub-groups in the population of interest.

 When a population is stratified, each stratum becomes an

independent population and you will need to decide the
sample size for each stratum.

 Any of the probability sampling methods mentioned in

this section can be used to sample within each stratum.

 The sampling method can vary from one stratum to another.

44
Stratified Random Sampling…
 A total sample size of n can be distributed to each stratum by

❶. Non- proportional or Equal allocation

 Allocate equal sample size to each stratum

❷. Proportionate allocation
n
n j  N j
N
 nj is sample size of the jth stratum
 Nj is population size of the jth stratum
 n = n1 + n2 + ...+ nk is the total sample size
 N = N1 + N2 + ...+ Nk is the total population size
45
Example
 Your study area has 3 villages with total population 1000.

 Village A has 200, village B has 500 and village C has 300
populations. Determine sample size for each village if total
sample size is 120.

 Village A=120/1000 X 200 = 24

 Village B =120/1000 X 500 = 60

 Village C =120/1000 X 300 = 36

46
Merits & Demerits of Stratified Sampling

Merits

 Improve the representativeness of the sample.

 Adequate representation of minority subgroups of

interest can be ensured.

Disadvantages

 Sampling frame for the entire population has to be

prepared separately for each stratum.

 Not suitable if there are no homogeneous subgroups. 47

Cluster Sampling
 Sometimes it is too expensive to carry out SRS
 Population may be large and scattered.

 Complete list of the study population unavailable.

 Travel costs can become expensive if interviewers have to survey

people from one end of the country to the other.

 In cluster sampling, selection of the required sample is done

on groups of study units instead of each study unit
individually.

48
Cluster Sampling…
 Cluster samples are generally used if:
 No list of the population exists.
 Well-defined clusters, which will often be geographic areas
exist.
 Often the total sample size must be fairly large to enable
cluster sampling to be used effectively.
 Mostly used for widely scattered population and if there is
no sampling frame
 It is preferable to select a large number of small clusters rather
49
than a small number of large clusters.
Steps in Cluster Sampling
 Cluster sampling divides the population into groups or
homogeneous clusters, unlike stratified sampling where the
strata are heterogeneous
 A number of clusters are selected randomly to represent the
total population and then all units within selected clusters are
included in the sample.
 No units from non-selected clusters are included in the
sample: they are represented by those from selected clusters.
 This differs from stratified sampling, where some units are
selected from each group. 50
Example
 In a school based study, we assume students of the same
school are homogeneous.

 We can select randomly sections and include all students of

the selected sections only.

51
Merits & Demerits of Cluster Sampling

Merits
 Sampling frame of the reference population is not required,
while a list of all clusters is either available or easy to create.
 Cost effective
Demerits
 Creates a loss of efficiency when compared with SRS.
 The researchers do not have total control over the final
sample size and the final size may be larger or smaller than
you expected. 52
Multistage Sampling
 Multistage sampling is used when the reference population is
large and widely scattered.

 Similar to the cluster sampling, except that it involves

picking a sample from within each chosen cluster, rather
than including all units in the cluster.

 No need of sampling frame for the reference population.

53
Multistage Sampling…
 This type of sampling requires at least two stages.

❶. The primary sampling unit (PSU) is the sampling unit in

the first sampling stage.
 In the first stage, large groups or clusters are identified and selected.
 These clusters contain more population units than are needed for
the final sample.

❷. The secondary sampling unit (SSU) is the sampling unit

in the second sampling stage, etc.
 In the second stage, population units are picked from within the
selected clusters (using any of the possible probability sampling
54
methods) for a final sample.
Multistage Sampling…
 If more than two stages are
used, the process of Woreda PSU
choosing population units
within clusters continues
Kebele SSU
until there is a final
sample.
HH TSU

55
Merits & Demerits of Multistage Sampling

Merits

 Multi-stage sampling saves a great amount of time and

effort by not having to create a list of all the units in a
population.

Demerits

 Sampling error is increased compared with a simple

random sample.

56
Sample Size Calculations

57
Sample Size
 Sample Size: The number of study subjects selected to
represent a given study population.

 Important to make inferences based on the findings from

the sample.

 Sample size should be sufficient to represent the

characteristics of interest of the study population.

58
Sample Size…
Common questions:
 “How many subjects should I study?”
 Widespread belief but not always true = “The bigger the
sample, the stronger the study”
 Too small sample = Waste of time and resources
 False conclusion

 Too large sample = Waste of resources, data quality

compromised
 Unnecessary involvement of extra subjects
59
 High cost and Time constraints
Sample Size Calculations
 Sample size determination depends on the:
 Objective of the study;

 Design of the study;

 Degree of precision required for generalization;

 Degree of confidence with which to conclude

 The absolute precision (d) is half of the confidence interval.

60
Estimating a Proportion
 In order to calculate the required sample size, you need to
know the following facts for proportion

A. Previous prevalence or proportion of the problem (p), If

you cannot guess the proportion, take it as 50%.

B. Allowable margin of error (d) (1% -5% ) - deviate from

the true proportion in the population as a whole.

C. Level confidence interval (95% or 99% )

61
Estimating a proportion…
D. The size of the population that the sample has to
represent.
 If it is more than 10,000 the precise magnitude is not likely to
be very important; but if the population is less than 10,000
then a smaller sample size may be required.
E. The difference between the two sub-groups and the
value of the likelihood or the power that helps in finding a
statistically significant difference.

62
Estimating a Proportion…
 Suppose that you are interested to know the proportion of
infants who breastfed >18 months of age in a rural area.
Suppose that in a similar area, the proportion (p) of breastfed
infants was found to be 0.20. What sample size is required to
estimate the true proportion within ±3% with 95%
confidence. Let p=0.20, d=0.03, α=5%

63
Estimating a proportion…
 Suppose there is no prior information about the proportion
who breastfeed

 Assume p=q=0.5 (most conservative)

 Then the required sample size increases

64
Estimating a Proportion…
 If sampling is from a finite population (<10,000) of size N, then

 Where n0 is the sample from an infinite population

 The initial sample size approached in the study may need to be
increased in accordance with the expected response rate, loss to
follow up, lack of compliance, and any other predicted reasons for
loss of subjects.
 Design effect for complex cluster sampling. Common values
multiply n by 1.5, 2, 3, …5.
 If you studied more than two dependent variable you have use the
65
variable which can give maximum sample size.
Thank
You