Chapter 5

Methods
 Contents
 Types of research design (Observational and experimental)
 Selection of study design
 Selection of target population
 Sampling and sampling techniques
 Identification and operationalization of research variables
 Research ethics
 Methods and procedure of data collection
 Data analysis, interpretation and synthesis
 Quality assurance techniques in research
 Work plan and budget break down
 Research findings dissemination
 Research methodology

 Research methodology is a way to

systematically solve the research problem. It
may be understood as a science of studying how
research is done scientifically
 The guiding principle for writing the Method
section is that it should contain sufficient
information for the reader to determine whether
the method is sound
 However, the methodology do not have to be
explain in great detail, but should justify its
significance over other methodologies.
 Components of research methodology

 Study setting
 Study design
 Target population
 Study population
 Sample size and sampling procedure
 Variables
 Operational definitions of key terms
 Tools/instrument.
 Data collection procedures
 Plan for analysis of data and interpretation of the results
 Ethical considerations

4
 Study setting

 It is related to the study area and other characteristics

which are more related to the study; add as a brief
background.

 Include map if possible (1-2 Paragraphs)

5
 Study design

 A study design is a specific plan or protocol for

conducting the study, which allows the investigator to
translate the conceptual hypothesis into an operational
one.

 The study design to be used should be appropriate for

achieving the objective of the study and should also be
clearly stated

6
There are two broad groups of research designs

1. Experimental
2. Non-experimental (observational)
 Experiment - Set of observations, conducted
under controlled circumstances, in which the
scientist (researcher) manipulates the condition
to ascertain what effect such manipulation has
on the outcome
 All experimental studies are longitudinal since
subjects are followed from exposure of
intervention to outcome

7
 Observational designs

 Cross-sectional/Surveys: the whole population or a

sample is studied
 Cohort Studies: subjects are selected with reference
to their exposure status and followed up
 Case Control Studies: Subjects are selected in
reference to their disease status.

8
 Things you need to consider when
choosing a study design

1. The objective/ the research question

2. The time you have
3. The money you have
4. The expertise you have
5. The requirements of an organization
 Population

 Broadly, population can be categorized as target

population and study population
 Target population: is a collection of items that have
something in common for which we wish to draw
conclusions at a particular time.
 In other words, there could be some elements of the target
population which are systematically excluded from the
study population and hence are not represented in the
sample
 Study Population: is a part of target population and
actually accessible and legitimate for data collection

10
 Sample size and sampling procedure

What is sampling?
 Sampling is the process involving the selection of a finite
number of elements from a given population of interest, for
purposes of inquiry.

11
What is a sample?

 A sample is a representative part of a population.

 In research it is not always possible to study an entire
population.
 A decision is often made, therefore, to study only a small
fraction of the population, or a “sample” of it, from which
conclusions can be drawn about the whole population.
 A sample should possess certain characteristics.

12
 What is Sampling?
What you want What you
to talk about Population actually observe
in the data

Sampling Process
Sampling Sample
Frame

Inference

Using data to say something (make an inference) with confidence, about a whole (population)
based on the study of a only a few (sample).

13
What are the characteristics a sample should possess?

 A sample should possess all the characteristics

of the population from which it is drawn, if
possible, so that is fully representative of the
population.

 The method of sample selection usually

determines its representative nature.

14
 Reasons for sampling:

1. Sampling for an exploratory purpose, in other words to

get a general impression of the total population of
interest.
› In this case the section of individuals to be included in
the sample can be quite subjective.
2. Sampling for purposes of obtaining estimates on certain
characteristics of the population.
› Here, the sampling process is undertaken through a
set of rigorous and objective procedures to avoid
subjective bias.

15
 Reasons that make sampling more useful
than complete enumeration:

 Several reasons make sampling more useful

than complete enumeration.
 These include considerations regarding:
 Time
 Costs and available resources, and
 Practicability

16
 Sampling methods

 There are two basic/general types of sampling

techniques:
1. Probability (or random)
2. non probability sampling
 The nature of your research study will determine which
type of sampling you should use.
 Large-scale descriptive studies almost always use
probability-sampling techniques.
 Intervention studies sometimes use probability sampling
but also frequently use non-probability sampling.
 Qualitative studies almost always use non probability
samples.

17
 Probability Sampling

 This is a sampling technique which employs random

procedures whereby the selection of the sampling unit (i.e.
the individuals, groups of people, objects, villages etc.
which are the basic unit of the sample) is done on the
basis of chance.

 This chance selection ensures that every member of the

population has an equal chance of being included in the
sample.

18
 Probability sampling is a technique you can use to
maximize external validity or generalizability of the results
of the study.

 Descriptive studies and large operational research

intervention studies are frequently designed so that their
results are as generalizable as possible.

19
 Non probability Sampling

 Non-probability sampling refers to the selection of a sample that

is not based on known probabilities.
 It is distinguished form probability sampling by the fact
subjective judgments play a role in selecting the sampling
elements.
 Non-probability sampling procedures are not valid for obtaining a
sample that is truly representative of a larger population.
 Almost always, non probability samples tend to over- select
some population elements and under-select others.
 When the known probabilities of selection are not known, there
is no precise way to adjust for such distortions.

20
The Sampling Design Process

i. Define the Target Population

ii. Determine the Sampling Frame

iii. Select a Sampling Technique

iv. Determine the Sample Size

v. Execute the Sampling Process

21
 Classification of Sampling Techniques
Sampling Techniques

Nonprobability Probability
Sampling Techniques Sampling Techniques

Convenience Judgmental Quota Snowball

Sampling Sampling Sampling Sampling

Simple Random
Systematic Stratified Cluster Multistage
Sampling
Sampling Sampling Sampling sampling

Stratified Cluster
Sampling

22
 Sample Size Determination
 Sample size determination differ with
› population size
› the type of variable being studied
› Study design
› type of statistical comparison planned

24
 In such cases we must consider the following
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?

25
 A good sample should be representative
 A REPRESENTATIVE SAMPLE has all the important
characteristics of the population from which it is drawn.

26
 Rules of thumb for determining the sample size
1. The larger the population size, the smaller the percentage of the
population required to get a representative sample
2. For smaller samples (N ‹ 100), there is little point in sampling. Survey
the entire population.
3. If the population size is around 500, 50% should be sampled.
4. If the population size is around 1500, 20% should be sampled.
5. Beyond a certain point (N = 5000), the population size is almost
irrelevant and a sample size of 400 may be adequate.

27
 Statistical Formula
 Sample size formula, in general, depends on the
number of study population:

 Single population

Two population

28
 Sample size for single population proportion

 If the study aims to be conducted on single population, then we

need the following
 What is the probability of the event occurring?

 How much error is tolerable (confidence interval)? How much precision do

we need?
 How confident do we need to be that the true population value falls within
the confidence interval?

29
 Z 2
 p (1  p )
n 2
2
d
 Where, n is the minimum sample size required
P is an estimate of the prevalence rate for the population
(%)
d is the margin of error to be tolerated (%)
 Za/2 is the standard normal variable at (1- )% confidence
level and is mostly 5% i.e., with 95% confidence level.

30
 Variables
 A variable is a characteristic of a person, object or phenomenon, which
can take on different values.
 These may be in the form of numbers (e.g. age) or non-numerical
characteristics (e.g. sex).
 A simple example of a variable in the form of numbers is ‘a person’s
age’.
› The variable ‘age’ can take on different values since a person can be 20
years old, 35 years old and so on.
 Other examples of variables are:
› weight (expressed in kilograms or in pounds);
› home - clinic distance (expressed in kilometers or in minutes walking distance);
› monthly income (expressed in Birr, or Dollars); and
› number of children (1, 2, etc.).

31
 Because the values of all these variables are expressed in
numbers, we call them Numerical Variables.
 Some variables may also be expressed in categories.
 For example, the variable sex has two districts categories,
groups, male and female.
 Since these variables are expressed in categories, we call
them Categorical Variables.

32
 How should variables for a particular study be selected?

 In a study with several possible variables, the variables

selected for a study are those which are directly relevant to
the objectives of the investigation.
 The number of variables should be as many as necessary,
and as few as possible.
 If too many variables are included for the study the
research may become difficult.

34
 Dependent and independent variables

 Variables can also be classified based on the cause-effect

relationships as: -

– Dependent

– Independent
 Independent variables

 Also called Exposure variable, explanatory variable

 Describe or measure the factors that are assumed to cause or
at least influence the problem.

E.g Does smoking cause lung cancer?

 The presumed cause = the independent variable
 Dependent variables

 Known as outcome variables

 Are those which depend on the status or position of the other
variable.
 Are the variables the researcher is interested in understanding,
explaining, or predicting.
 The presumed effect = the dependent variable.
 Dependent variables

 Variability in the dependent variable depends on variability in

the independent variable.
 Independent Dependent variable
 Exposure Outcome
 Operationalzing variables

 Many variables can easily be measured

 For some variables it is some times not possible to find
meaningful categories unless the variables are made
operational with one or more indicators
 Operationalizing variables means that you make them
measureable
 Ex- determining level of knowledge
 Operational zing variables…

 There is a need to develop a series of questions to assess

knowledge
 The answer to these questions form an indicator of someone’s
knowledge on the issue, which can then be categorized
 Operational zing variables…

 E.g if 10 questions were asked, you might decide that the

knowledge of those with:
› 0 to 3 correct answers is poor

› 4 to 6 correct answers is reasonable, and

› 7 to 10 correct answers is good

42