Sampling

Tigist Birie (BSC, MPH)

07/30/2024 sampling 1
 Session Objectives

BY the end of this session learners will able to:

1. Define sampling
2. Describe the importance of sampling
3. Identify different types sampling
4. Discuss advantages and limitations of different
sampling techniques
5. Describing errors associated with sampling?

07/30/2024 sampling 2
 What is sampling?

• A process by which we study a small part of

a population (sample) to make judgments
about the entire population

• Sampling involves selecting a number of

units from a defined population

07/30/2024 sampling 3
 Why Do We Sample ?
Advantages of sampling
 REDUCED COST: ↓demands on resources Eg. Material

 GREATER ACCURACY: lead to better accuracy of

collecting data.
 GREATER SPEED: data collected & summarized quickly.

 FEASIBILITY: the only feasible method of collecting data.

 FACS
07/30/2024 sampling 4
 Drawback of Sampling
• There is always a sampling error.
• Sampling may create a feeling of discrimination
with in the population.
• Sampling may be inadvisable where every unit in
the population is legally required to have a record.

07/30/2024 sampling 5
 Sampling questions

• What is the group of people (STUDY POPULATION) we are

interested in from which we want to draw a sample?
• How many people do we need in our sample?
• How will these people be selected?

07/30/2024 sampling 6
 Terminology

• Target Population
– The complete set of individuals or members of a group of
interest (define clearly, different units (not always people))
• Sample/study population
– A subset of the population that you select to study
• Sampling units
– The elements of the population that are selected
• Individual people, health facilities, districts
• Sampling frame
– The list of units of the population from which the sample is drawn
07/30/2024 sampling 7
 Types of sampling
• Probability
– Subjects are selected using the process of random
selection
– Chances of selecting a subject are known
• Non-probability
– Subjects are selected using other means than
random selection
– Chances of selecting a subject are not known

07/30/2024 sampling 8
 Probability sampling
• A probability sampling:- selection of a sample
from a population, based on the principle of
randomization or chance.
• Valid and reliable inferences about the population
can be made
• Is more complex, more time-consuming and
usually more costly than non-probability sampling
.
• Used when it’s desirable and possible to
generalize to a larger population
07/30/2024 sampling 9
 Probability sampling cont..
The method selection depend on
• the available sampling frame,
• how spread out the population is,
• how costly it is to survey members of the
population and
• how users will analyze the data.
Each element of the population has a known
non-zero probability of selection
07/30/2024 sampling 10
 Non probability sampling
• 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.

07/30/2024 sampling 11
 When to use Non probability Sampling?

• Difficult or impossible to obtain the list of names

for sampling (Homeless, IV Drug user).
• All of the cases of interest may not be identified
ahead of time.
• For rare population.

07/30/2024 sampling 12
 Advantages
• Used when a sampling frame does not exist.

• they are quick, inexpensive and convenient.

• Good for pretests, pilot studies, In-depth

interviews.

• Used when Precise representativeness is not

necessary.

07/30/2024 sampling 13
 Disadvantage
• No random selection (unrepresentative).

• Reliability cannot be measured.

• No way to measure the precision of the

resulting sample.

• Inappropriate for generalizing findings.

07/30/2024 sampling 14
 Classification of Sampling Simple random
Methods Systematic
Probability
sampling Stratification
MCSSS
Cluster

Sampling Multistage
methods
Convenient

Judgmental/
Non-
purposive
probability
sampling
Quota

Snowball
07/30/2024 sampling 15
 Simple Random Sample
• A list (sampling frame) of all members of the
target population is made using a lottery
system or a random numbers table, individual
units are selected until the sample size is
achieved
• Ex: Sample of 20 out of 100 randomly selected

07/30/2024 sampling 16
 Advantages and Disadvantages
Advantages
• The formulas are easy to use.
• Easy to apply to small populations.
Disadvantages
• Requires a list of the population
• Can be an expensive and unfeasible for large populations –
need complete list.
• May miss or under sample key subsets(Minority
subgroups)
• Used in situations where the number of sampling
units is relatively small
07/30/2024 sampling 17
 Systematic Sampling
• Individuals are chosen at regular intervals
from an ordered list.
• Determine units available for sampling: i.e.
Study population of 100 individuals
• Decide on sample size: i.e. Sample 25
individuals
• Calculate sampling interval 100/25=4
• Start at random student between 1 and 4, i.e.
3 the sampling frame
07/30/2024 sampling 18
 Advantages and Disadvantages
Advantages:
• Easy to select the sample
• Might be more representative than SRS –sample evenly
spread over reference population
• Under “most” conditions it can be analyzed as SRS
• Useful when elements can’t be listed prior to selection
 Require less time than SRS

Disadvantages:
• Sample may be biased if hidden periodicity in
population coincides with that of selection.
• Difficult to assess precision of estimate from one survey.
07/30/2024 sampling 19
 Stratified Sampling
 It is appropriate when the distribution of the
characteristic to be studied is heterogeneous.
 The population is divided into groups called
strata having similar characteristics.

 Maximum homogeneity within the group and

max. heterogeneity among the groups
contribute for the accuracy of the estimates .

07/30/2024 sampling 20
 STRATIFIED SAMPLING

• Each stratum is then sampled as an independent sub-population,

out of which individual elements can be randomly selected.
• Every unit in a stratum has same chance of being selected.
• Using same sampling fraction for all strata ensures proportionate
representation in the sample.
• Adequate representation of minority subgroups of interest can be
ensured by stratification & varying sampling fraction between
strata as required.

07/30/2024 sampling 21
 Stratified
Stratified Random
Random Sample:
Sample: Population
Population
of
of FM
FM Radio
Radio Listeners
Listeners
Stratified by Age

20 - 30 years old
(homogeneous within)
(alike) Hetergeneous
(different)
30 - 40 years old between
(homogeneous within)
(alike) Hetergeneous
(different)
40 - 50 years old between
(homogeneous within)
(alike)

07/30/2024 sampling 22
 Types of stratification
• Equal allocation (could require weighting)

• Proportionate – self-weighting

07/30/2024 sampling 23
 Stratified Random Sample
• Population is divided into non-overlapping
subpopulations called strata
• A random sample is selected from each stratum
• Potential for reducing sampling error
• Proportionate -- the percentage of the sample taken
from each stratum is proportionate to the percentage
that each stratum is within the population
• Disproportionate -- proportions of the strata within
the sample are different than the proportions of the
strata within the population

07/30/2024 sampling 24
 Steps in Drawing a Stratified Random
Sample
1: Divide the target population into
homogeneous subgroups or strata
2. Decided which type of stratified sampling to
use
3. Distribute the total sampling for each strata
4: Draw random samples from each stratum
5: Combine the samples from each stratum
into a single sample of the target population

07/30/2024 sampling 25
 • There are two methods to get the study subject
from each subgroup, proportional allocation or
equal allocation as we have seen before.

• We use proportional allocation technique when

our subgroups vary dramatically in size in our
population

07/30/2024 sampling 26
07/30/2024 sampling 27
 Stratified Sampling

Advantages
• Can improve reliability and precision of estimates
(eliminates variability across strata)
• Improves the accuracy of estimation
• Efficient
Disadvantages:
• Might need sampling weights
• Sampling frame of entire population has to be
prepared separately for each stratum – costly
• Not useful when there are no homogeneous
subgroups
07/30/2024 sampling 28
 Cluster sampling

• Is a sampling technique used when "natural"

groupings are evident in a statistical population.

• Reference population (homogeneous) is divided into

clusters – often geographical units

• Clusters are often geographic units (e.g., districts,

villages) or organisational units (e.g., clinics, training

groups).
07/30/2024 sampling 29
 CLUSTER SAMPLING
• Cluster sampling is an example of 'two-stage
sampling' .
• First stage a sample of areas is chosen;
• Second stage a sample of respondents within
those areas is selected.
• Sampling units are groups rather than individuals.
• A sample of such clusters is then selected.
• All units from the selected clusters are studied.

07/30/2024 sampling 30
 Cluster

• Example: Instead of sampling TB patients randomly in a country

from a list of all TB patients, you could randomly sample facilities
with TB services and interview all TB patients in that facility
• Multi-stage cluster

– 1st –PTB service facilities (primary sampling

unit)
– 2nd – TB patients in facilities (secondary
sampling unit)
07/30/2024 sampling 31
 Cluster Sample
• The population is divided into subgroups
(clusters) like families. A simple random
sample is taken of the subgroups and then all
members of the cluster selected are surveyed.

07/30/2024 sampling 32
 Advantages and Disadvantages
Advantages
• Cuts down on the cost of preparing a sampling
frame.
• This can reduce travel and other administrative
costs.
Disadvantages
• sampling error is higher for a simple random
sample of same size.
• Units within clusters may be less variable than the
population as a whole making cluster sampling
less precise than a simple random sample of the
same size
07/30/2024 sampling 33
 D ifern ceB etw en S tran d C lu ster

• Although strata and clusters are both non-overlapping

subsets of the population, they differ in several ways.

• All strata are represented in the sample; but only a

subset of clusters are in the sample.

• With stratified sampling, the best survey results occur

when elements within strata are internally
homogeneous. However, with cluster sampling, the
best results occur when elements within clusters are
internally heterogeneous
07/30/2024 sampling 34
 MULTISTAGE SAMPLING
• Complex form of cluster sampling in which two or
more levels of units are embedded one in the other.
• First stage, random number of districts chosen in all
states.
• Followed by random number of kebeles, villages.
• Then third stage units will be houses.
• All ultimate units (houses, for instance) selected at
last step are surveyed.
07/30/2024 sampling 35
 MULTISTAGE SAMPLING……..
• This technique, is essentially the process of taking
random samples of preceding random samples.
• Not as effective as true random sampling, but probably
solves more of the problems inherent to random
sampling.

• An effective strategy because it banks on multiple

randomizations. As such, extremely useful.
• Multistage sampling used frequently when a complete list
of all members of the population not exists and is
inappropriate.

07/30/2024 sampling 36
 Multi-Stage Sampling
• Moreover, by avoiding the use of all sample
units in all selected clusters, multistage
sampling avoids the large, and perhaps
unnecessary, costs associated with
traditional cluster sampling.
• Cluster (area) random sampling can be multi-
stage.
• Any combinations of single-stage methods.

07/30/2024 sampling 37
 Multistage …

• For example, in a study of utilisation of pit latrines

in a district 150 homesteads are to be visited for
interviews with family members as well as for
observations on types and cleanliness of latrines.
• The district is composed of 6 wordas and each
woreda has between 6 and 9 villages.

07/30/2024 sampling 38
 Multistage …

• The following four-stage sampling procedure could be

performed*:

1. Select 3 wordas out of the 6 by simple random sampling.

2. For each worda select 5 villages by simple random

sampling (15 villages in total).

3.For each village select 10 households.

07/30/2024 sampling 39
 Representativeness

• The sample has approximately the same

characteristics of the population relevant to the
research in question
• How representative your sample is to the
target population influences your ability to
generalize your findings.

07/30/2024 sampling 40
 Factors Influencing sample representativeness

Sampling procedures
• Does the sampling frame represent the population to
which you want to generalize
Sample size
• The larger the sample size the closer to the population
Participation rates (response rates)
• If you have low participation, those who participate
and those who do not could be systematically
different.
• E.g. Of a sample of 1000, only 640 participated (64%)
07/30/2024 sampling 41
 Non-Probability Sampling

07/30/2024 sampling 42
 Convenience Sampling

• Involves the sample being drawn from that part

of the population which is close to hand. That
is, readily available and convenient
– Happen to be present at a given time and place
– Least desirable because findings only concern those
who responded

07/30/2024 sampling 43
 CONVENIENCE…

• Sometimes known as opportunity sampling or

accidental or haphazard sampling.
• The researcher using such a sample cannot
scientifically make generalizations about the total
population from this sample because it would not be
representative enough.
• This type of sampling is most useful for pilot
07/30/2024 sampling 44
testing.
 Judgment /Purposive Sampling
• Individuals are selected based on specific characteristics

• Deliberately selected to provide specific information about a

particular population

• Commonly used in qualitative research where strict statistical

generalization is not necessarily the goal

• Often used in clinical research and other experimental studies

– External validity less important than internal validity

07/30/2024 sampling 45
 Purposive Sampling…
• In purposive sampling, each sample element is selected for a
purpose, usually because of the unique position of the sample
elements.

• Purposive sampling may involve studying the entire population of

some limited group (directors of shelters for homeless adults) or a
sub-set of a population (mid-level managers with a reputation for
efficiency).

• Or a purposive sample may be a “key informant survey,” which

targets individuals who are particularly knowledgeable about the
issues under investigation.
07/30/2024 sampling 46
 Snowball
• Special type of non-probability sampling
– Useful in hard to reach populations
– Select one member of target population
• Ask him/her to refer members of the same group for
participation

• It can be used to sample members of such groups as drug

dealers, prostitutes, practicing criminals, participants in
Alcoholics Anonymous groups, gang leaders, informal
organizational leaders, and homeless persons.
07/30/2024 sampling 47
 Snowball Sampling

Prone Cons
• May be able to find • May run into a “vein” or
difficult to locate network which isn’t at
groups all representative of
such kinds of people

07/30/2024 sampling 48
07/30/2024 sampling 49
 Quota Sampling

• Quota sampling is intended to overcome the most obvious

flaw of availability sampling—that the sample will just consist
of whoever or whatever is available, without any concern for its
similarity to the population of interest.

• The distinguishing feature of a quota sample is that quotas are

set to ensure that the sample represents certain characteristics in
proportion to their prevalence in the population.

07/30/2024 sampling 50
 Quota Sampling

• Pros • Cons
• Although don’t know • Take more effort than
“odds…” experience many
shows it’s typically • Need trustworthy poll
“pretty good” takers

07/30/2024 sampling 51
 Quota Sampling, continued…
The problem is that even when we know that a quota sample
is representative of the particular characteristics for which
quotas have been set, we have no way of knowing if the
sample is representative in terms of any other characteristics.

For example, quotas have

been set for gender only.
Under the circumstances,
it’s no surprise that the
sample is representative
of the population only in
terms of gender, not in
terms of race. Interviewers
07/30/2024 sampling
are only human;. 52
 Errors in sampling:

Total error in = Sampling + Nonsampling

sampling Error Error

Due to selecting a Due to mistakes or

sample instead of systematic deficiencies
surveying the in sampling, due to
entire population sampling design
problems
 Sampling error(random error)
• Sampling error is the difference between an estimate of a
population parameter (calculated with data from a sample) and
the true population parameter being estimated
– True population mean from entire distribution

– Estimated mean calculated from the sample

• In a sample survey, we are collecting data from a subset of the

population, i.e., we do not observe the whole population
– Estimate for any one sample is unlikely to perfectly match
the population parameter
 Non sampling error(bias):

• Non sampling error includes all errors in

sample selection due to:
– Frame error
• Mismatch between target population and sampling
frame (see earlier)
– Non response error
• Inability to obtain response from a sampled unit
 Reducing total error in sampling:
• Sampling error
– Choose a sample design that produces precise
estimates
– Stratified random sampling is more precise and
sometimes far more precise than SRS
– Increase sample size
– Make population to be similar (homogenous)
• Non sampling error
– Choose survey methods that encourage complete and
accurate responses (non response)
– Choose a frame close to target population (frame)