Sampling methods for health science students

1. Sampling Methods
Daniel Bekele (BSc in Public Health, MPH /Biostatistics)
Department of public health
Debre Markos University
dabekle121@gmail.com
November 3, 2018

2. Learning Objectives
At the end of this chapter, the students will be able to:
Define population and sample and understand the different sampling
terminologies
Differentiate between probability and Non-Probability sampling
methods and apply different techniques of sampling
Understand the importance of a representative sample
Differentiate between random error and bias
Enumerate advantages and limitations of the different sampling
methods 2

3. Sampling
 Sample: is a group of people, objects, or items that are taken from
a larger population for measurement.
 The sample should be representative of the population to ensure
that we can generalize the findings from the research sample to the
population as a whole.
3

4. Sampling method cont’d..
 Sample design: is a definite plan for obtaining a sample from a given
population. It refers to the technique or the procedure the researcher
would adopt in selecting items for the sample.
 Sampling: refers to strategies that enable us to pick a subgroup from
a larger group and then use this subgroup as a basis for making
inferences about the larger group.
 The researcher's goal is always to generalize about the population
based on observations of the sample.
4

5. Basic Terms
 Reference population:(also called source population or target
population): is a group of individuals/persons, objects, or items
from which samples are taken for measurement.
 For example a population of presidents or professors, books or students.
 It refers to the entire group of individuals or objects to which
researchers are interested in generalizing the conclusions.
5

6. Basic term cont’d
6

7. Basic term cont’d
Target and study population and sample
7

8. Basic term cont’d
 Census: Obtained by collecting information about each member of a
population
 Study population: the population included in the sample.
 Sampling unit: the unit of selection in the sampling process
 Study unit: the unit on which information is collected.
 Sampling Frame: is the list of units from which the sample is taken
 It should be comprehensive, complete and up-to date.
 Examples of sampling frame: Electoral Register; Postcode Address File;
telephone book and so on.
8

9. Basic term cont’d
 Sampling fraction (Sampling interval): the ratio of the
number of units in the sample to the number of units in the
reference population (n/N)
 Steps in Sampling Design
 There are steps that we need to follow to get in to the respondents.
 What is the target population?
 Define the target population and study population.
 What are the parameters of interest?
 Define the parameters of interest of the study.
 What is the sampling frame?
 Select the sampling frame.
9

10. Steps in Sampling Design
 What is the appropriate sampling method?
 Determine which sampling method we are going to use depending on the
setting of the population and the purpose of the study.
 Plan procedures to select the sampling unit
 Determine the size of the sample which will be selected from the
population.
 Select actual sampling unit
 Conduct field work
10

11. Advantages of sampling
• Feasibility: Sampling may be the only feasible method of collecting
the information.
• Reduced cost: Sampling reduces demands on resource such as
finance personnel and material resource.
• Greater accuracy: Sampling may lead to better accuracy of collecting
data accuracy of collecting data
• Sampling error: Precise allowance can be made for sampling error
• Greater speed: Data can be collected and summarized more quickly11

12. Disadvantages of sampling
 There is always a sampling error
 Sampling may create a feeling of discrimination with in the
population discrimination within the population.
 If sampling is biased, or not representative or too small the
conclusion may not be valid and reliable
 Sampling may be inadvisable where every unit in the population is
legally unit in the population is legally required to have a record.
12

13. Sampling methods
There are many methods of sampling when doing
research.
One of the most important decisions that any researcher makes is how
to obtain the type of participants needed for the study.
The sample that we draw for our study determines the generalizability of
our findings.
There are many methods of sampling when doing research.
13

14. 1. Probability sampling
 Probability sampling is based on the concept of random selection,
whereas non-probability sampling is ‘non-random’ sampling.
14

15. 1. Probability sampling methods…
 Probability sampling strategies typically use a random or chance
process in sampling.
 The "equal chance" and "independent" components of random
sampling are what makes us confident that the sample has reasonable
chance of representing the population
 Generalization is possible (from sample to population)
 A sampling frame exists or can be compiled.
15

16. 1. 1. Simple random sampling
 Simple random sampling is the most straightforward of the random
sampling strategies.
 We use this strategy when we believe that the population is relatively
homogeneous for the characteristic of interest.
 To use SRS there should be frame for the population
 Each unit in the sampling frame has an equal chance of being selected
 Representativeness of the sample is ensured.
16

17. 1.1. Simple random sampling cont’d
 Procedures to select the sample
 Depending on the complexity of the population, we can use
different tools to select n samples from the frame.
 Lottery method,
 Table of random number
 Computer generated random number
 Lottery method is appropriate if the total population is not too large,
otherwise if the population is too large then it will be very difficult to
use lottery method
17

18. 1.1. Simple random sampling cont’d
 Table of random number or computer generated random number is
the feasible method to be used.
Examples
 Suppose your school has 500 students and you need to conduct a
short survey on the quality of the food served in the cafeteria.
 You decide that a sample of 50 students should be sufficient for
your purposes
 In order to get your sample, you assign a number from 1 to 500 to
each student in your school.
18

19. 1. 1. Simple random sampling cont’d
 To select the sample, you use a table of randomly generated
numbers.
 Pick a starting point in the table (a row and column number) and
look at the random numbers that appear there. In this case, since
the data run into three digits, the random numbers would need to
contain three digits as well.
 The first 50 different numbers between 001 and 500 make up your
sample.
19

20. 1.2. Systematic random sampling
20

21. 1.2. Systematic random sampling cont’d
21

22. 1.2. Systematic random sampling cont’d
 Then the selected list will be
a, a+k, a+2k, a+3k, …,
 Example
Example systematic sampling
22

23. 1.2. Systematic random sampling cont’d
 Demerits of systematic random sampling
 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.
 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.
23

24. 1.3. Stratified Random Sampling
 Stratified random sampling is used when we have subgroups in our
population that are likely to differ substantially in their responses or
behavior (i.e. if the population is heterogeneous).
 In stratified random sampling, the population is first divided into a
number of parts or 'strata' according to some characteristic, chosen to
be related to the major variables being studied.
 A separate sample is then taken independently from each stratum, by
simple random or systematic sampling.
24

25. 1.3. Stratified Random Sampling
 Steps involve in stratified sampling method:
 Define the population
 Determine the desired sample size
 Identify the variable and subgroups (strata) for which
 you want to guarantee appropriate representation (either proportional or equal)
 Classify all members of the population as a member of one of the identified
subgroups
 Randomly select (using simple random sampling or others) an appropriate
number of individuals from each subgroup.
 Then the total sample size will be the sum of all samples from each subgroup
25

26. 1.3. Stratified Random Sampling cont’d
 There are two methods to get the study subject from each subgroup,
proportional allocation or equal allocation.
 We use proportional allocation technique when our subgroups vary
dramatically in size in our population.
26

27. 1.3. Stratified Random Sampling cont’d
27

28. 1.3. Stratified Random Sampling cont’d
 Advantage of stratified sampling
 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
28

29. 1.4. Cluster Random Sampling
 In this sampling scheme, selection of the required sample is done on
groups of study units (clusters) instead of each study unit individually.
 The sampling unit is a cluster, and the sampling frame is a list of these
clusters.
 If the study covers wide geographical area, using the other methods
will be too costly.
 The idea is, divided the total population in to different clusters and
then the unit of selection will be cluster. Then, total population in the
selected cluster will be taken as the sample.
29

30. 1.4.Cluster Random Sampling cont’d
 Steps in cluster sampling are:
 Define the population
 Determine the desired sample size
 Identify and define a logical cluster (can be kebele, Got,residence,
and so on)
 Make a list of all clusters in the population
 Estimate the average number of population number per cluster
 Determine the number of clusters needed by dividing the sample
size by the estimated size of the cluster
 Randomly select the required number of clusters (using table of
random number as the total number of clusters is manageable)
 Include in the sample all population in the selected cluster . 30

31. 1.4. Cluster Random Sampling cont’d
 CRS
31

32. 1.4. Cluster Random Sampling cont’d
 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 random32

33. 1.5. Multi-stage sampling
 This method is appropriate when the reference population is large
and widely scattered.
 Selection is done in stages until the final sampling unit (eg.,
households or persons) are arrived.
 The primary sampling unit (PSU) is the sampling unit (usually large
size) in the first sampling stage
 The secondary sampling unit (SSU) is the sampling unit in the second
sampling stage, etc.
 This is the most complex sampling strategy.
33

34. 1.5. Multi-stage sampling cont’d
 Example
 Suppose we want to investigate the working efficiency of nationalized
health institutions in Ethiopia and we want to take a sample of few
health institutions for this purpose.
 The first stage is to select large primary sampling unit such as region
in a country.
 Then we may select certain zones and interview all health institutions
in the chosen districts. This would represent a two-stage sampling design
with the ultimate sampling units being clusters of districts. 34

35. 1.5. Multi-stage sampling cont’d
 Merit
 Cuts the cost of preparing sampling frame
 Demerit
 Sampling error is increased compared with a simple random
sample.
 Multistage sampling gives less precise estimates than sample random
sampling for the same sample size, but the reduction in cost usually
 Far outweighs this, and allows for a larger sample size.
35

36. 2. Non-Probability Sampling Method
 In the presence of constraints to use probability sampling strategies,
the alternative sampling method is non-probability sampling method.
 Non-probability sampling strategies are used when it is practically
impossible to use probability sampling strategies.
 Non-probability sampling is sampling procedure which does not
afford any basis for estimating the probability that each item in the
population has of being included in the sample.
36

37. 2.1. purposive sampling
 In purposive sampling, we sample with a purpose in mind.
 When the desired population for the study is rare or very difficult to
locate and recruit for a study, purposive sampling may be the only
option.
 For example, you are interested in studying cognitive processing
speed of young adults who have suffered closed head brain injuries in
automobile accidents.
 This would be a difficult population to find.
37

38. 2.2. Convenience Sampling
 Convenience sampling is sometimes referred to as haphazard or
accidental sampling
 It is not normally representative of the target population because
sample units are only selected if they can be accessed easily and
conveniently.
 The obvious advantage is that the method is easy to use, but that
advantage is greatly offset by the presence of bias.
38

39. 2.3. Judgment Sampling
 The researcher selects the sample based on his/her judgment.
 The critical issue here is objectivity: how much can judgment be relied
upon to arrive at a typical sample ?
2.4. Quota sampling
 Is a method that ensures a certain number of sample units from d/f
categories with specific characteristics are represented.
 In this method the investigator interviews as many people in each
category of study unit as he can find until he has filled his quota.
 It is the non-probability equivalent of stratified sampling. This differs
from stratified sampling, where the stratums are filled by random
sampling.
39

40. 2.5. Snowball sampling
 It is a special non-probability method used when the desired
sample characteristic is rare.
 Snowball sampling relies on referrals from initial subjects to
generate additional subjects.
 What we need to do in case of snowball sampling is that first
identify someone who meets the criteria and then let him/her
bring the others he/she knew.
 It comes at the expense of introducing bias because the
technique itself reduces the likelihood that the sample will
represent a good cross section from the population. 40

41. Sampling error
 A sample is expected to mirror the population from which it comes,
however, there is no guarantee that any sample will be precisely
representative of the population.
 The uncertainty associated with an estimate that is based on data
gathered from a sample of the population rather than the full
population is known as sampling error.
 Sampling errors are the random variations in the sample estimates
around the true population parameters.
 Sampling error (chance )
 Can not be avoided or totally eliminated
 Sampling error decreases with the increase in the size of the sample,
and it happens to be of a smaller magnitude in case of homogeneous
population. When n = N sampling error = 0⇒ 41

42. Non Sampling Error (Measurement Error)
 It is a type of systematic error in the design or conduct 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 non-sampling error (bias) by careful
design of the sampling procedure and not by increasing the sample
size.
 It can occur whether the total study population or a sample is being
used.
 It is a type of systematic error in the design or conduct of a sampling
procedure which results in distortion of the sample, so that it is no
longer representative of the reference population.
 It may either be produced by participants in the study or be simply a
by product of the sampling plans and procedures 42

43. Non Sampling Error cont’d
 It may either be produced by participants in the study or be simply a
by product of the sampling plans and procedures
 These biased observations can be very devastating to
the findings of the study.
 Example: If you take male students only from a student dormitory in
Ethiopia in order to determine the proportion of smokers, you
would result in an overestimate, since females are less likely to
smoke.
 Increasing the number of male students would not remove the
bias.
43

44. The Cause of Non-Sampling Error
 The interviewers effect
 The respondents effect
 Non-response: It is the failure to obtain information on some of the
subjects included in the sample to be studied. Non response results in
significant bias when the following two conditions are both fulfilled.
 When non-respondents constitute a significant proportion of the sample
(about 15% or more)
 When non-respondents differ significantly from respondents.
 Thus , the total survey error is the sum of both sampling error
and non-sampling error.
44

45. The Cause of Non-Sampling Error cont’d
 There are several ways to deal with this problem and reduce the
possibility of bias:
a) Data collection tools (questionnaire) have to be pre-tested.
b) If non response is due to absence of the subjects, repeated attempts
should be considered to contact study subjects who were absent at the
time of the initial visit.
c) To include additional people in the sample, so that non respondents
who were absent during data collection can be replaced (make sure
that their absence is not related to the topic being studied).
45

46. Thank You