61

Research Methods
 This section should include:
Justification for a qualitative or quantitative
approach
The methods (or tools) you will use.
Reliability and validity of instruments
sources of data,
how you will collect them (e.g. interviews,
surveys) and
Operational definitions
the statistical methods of data analysis
Variables in the study
Inclusion and exclusion
62
 Research Methods versus
Methodology
 Research methods may be understood as all those
methods/techniques that are used for conduction of
research.
 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.
 Thus, when we talk of research methodology we not only talk of
the research methods but also consider the logic behind the
methods we use in the context of our research study and
explain why we are using a particular method or technique and
why we are not using others so that research results are capable
of being evaluated either by the researcher himself or by others.

63
Types of study designs
 A study design is the process that guides
researchers on how to collect, analyze
and interpret observations.
 It is a logical model that guides the investigator in
the various stages of the research.

64
Study Designs Classification

 Descriptive Designs
◦ Case report/ case series
◦ Cross sectional
◦ Ecological
 Analytic Designs
◦ Observational
 Case control
 Cross sectional
 Cohort
◦ Interventional
 Quasi-experimental
 Experimental
 Study designs could be exploratory,
descriptive or analytical
65
 Non-intervention (Observational)
studies
 The researcher just observes and analyses
researchable objects or situations but
does not intervene; and

Intervention studies
• The researcher manipulates objects or
situations and measures the outcome of his
manipulations (e.g., by implementing intensive
health education and measuring the
improvement in immunization rates.)
66
Exploratory studies
 An exploratory study is a small-scale study
of relatively short duration, which is
carried out when little is known about a
situation or a problem.
 It may include description as well as
comparison.
◦ If the problem and its contributing factors are not
well defined it is always advisable to do an
exploratory study before embarking on a large-
scale descriptive or comparative study.
 Example: A national AIDS Control
Programme wishes to establish counseling
services for HIV positive and AIDS patients,
but lacks information on specific needs
patients have for support. 67
Descriptive studies:
 Descriptive studies may be defined as studies that
describe the patterns of disease occurrence and
other health-related conditions by person place
and time.
 Most basic demographic studies, disease
frequency and distribution
 Personal characteristics: basic demographic
factors, such as age, sex, marital status or
occupation, as well as the consumption of various
types of food or medication use.
 Characteristics of place: the geographic
distribution of disease, including variation among
countries or within countries, such as between
urban and rural areas.
 Time: seasonal patterns in disease onset, etc.
68
Uses of descriptive studies
 They can be done fairly quickly and easily.
 Allow planners and administrators to
allocate resources
 Provide the first important clues about
possible determinants of a disease (useful
for the formulation of hypotheses)

69
Types of descriptive studies
a) Case reports and case series
 Case report: a careful, detailed report by one or
more clinicians of the profile of a single patient.
 The individual case report can be expanded to a
case series, which describes characteristics of a
number of patients with a given disease.
 Uses
◦ One of the first steps in outbreak investigation
◦ Often useful for hypothesis generating and examining
new diseases, but conclusions about etiology cannot
be made.

70
b) Ecological studies:
• Data from entire populations are used to
compare disease frequencies between
different groups during the same period
of time or in the same population at
different points in time.
• Example: Countries with low cigarette
consumption have lower lung cancer rates
than those countries with high cigarette
consumption.

71
c) Cross-sectional studies
 A cross-sectional (prevalence) study provides
information concerning the situation at a given time.
 In this type of study, the status of an individual with
respect to the presence or absence of both
exposure and disease is assessed at the same point
in time.
 Usually involve collection of new data.
 In general, measure prevalence rather than
incidence
 Not good for studying rare diseases or diseases with
short duration; also not ideal for studying rare
exposures.
 Nowadays, there is an increasing emphasis on the
value of longitudinal studies in which observations
are repeated in the same community over a
prolonged period (i.e., longitudinal studies provide the
required data at more than one point in time
unlike cross- sectional surveys).
72
Analytic studies
 Analytic studies may be defined as studies
used to test hypotheses concerning the
relationship between a suspected risk
factor and an outcome and to measure
the magnitude of the association and
its statistical significance.
 Can be: Observational and intervention.

73
Observational studies
 No human intervention involved in
assigning study groups; simply observe
the relationship between exposure and
disease.
 Subject to many potential biases, but by
careful design and analysis, many of these
biases can be minimized.
 Examples of observational studies:
comparative cross-sectional, cohort
and case-control studies.
74
a) Comparative cross-sectional studies:
 A cross-sectional study can be either analytical or
descriptive, according to its purpose.
 If data are collected both on exposures and
outcomes of interest, and if the data are analysed
so as to demonstrate differences either between
exposed and non-exposed groups, with respect
to the outcome, or between those with the
outcome and those without the outcome, with
respect to the exposure, then this is an analytical
cross-sectional study.
 If the information collected is purely of a
descriptive nature, not involving the comparison
of groups formed on the basis of exposure or
outcome status, then this is a descriptive cross-
sectional study.
75
b) Cohort studies:
Study groups identified by exposure
status prior to ascertainment of their
disease status and both exposed and
unexposed groups followed in identical
manner until they develop the disease
under study, they die, the study ends, or
they are lost to follow-up.

76
Strengths and limitations of the cohort study design

Strengths:
 Is of particular value when the exposure is rare
 Can examine multiple effects of a single exposure
 Allows direct measurement of incidence of disease
in the exposed and non-exposed groups.
Limitations:
 Is inefficient for the evaluation of rare diseases
 Expensive and time consuming
 Unexpected environmental changes may
influence the association
 Validity of the results can be seriously affected by
Non response, migration and loss-to-follow-
up biases
77
 Advantages of Cohort Studies

 Can measure disease incidence

 Accurate relative risk (risk ratio) estimation
 Can examine rare exposures
 Temporal relationship can be inferred
(prospective design)
 Magnitude of a risk factor’s effect can be
quantified
 Ascertainment of exposure is made
 Multiple outcomes can be studied (smoking, lung
cancer, COPD, larynx cancer)
Prospective cohort study
Disease
Exposure Study starts occurrence

time

Disease
Study starts Exposure occurrence

time
 Retrospective cohort studies

Disease
Exposure Study starts
occurrence

time
c) Case-control studies:
 Group of subjects with the disease
(cases) and group of subjects without the
disease (controls) are identified.
 Information, about previous exposures
are obtained for cases and controls, and
frequency of exposure compared for the
two groups.

81
Strengths and limitations of the case-control study design

Strengths:
 Is relatively quick and inexpensive
 Is optimal for the evaluation of rare diseases.
 Can examine multiple etiologic factors for a
single disease.
Limitations:
 Is inefficient for the evaluation of rare exposures
 Cannot directly compute incidence rates of
disease in exposed and non- exposed individuals.
 Is particularly prone to bias compared with other
analytic designs, in particular, selection and recall
bias, misclassification
 Reverse causation is a problem in
interpretation
82
 Case-Control Studies

Exposed
Not
Cases
exposed
Population
Exposed Controls
Not
exposed
Case-Control Studies
Intervention studies
 In intervention studies, the researcher manipulates a
situation and measures the effects of this
manipulation.
 Usually (but not always) two groups are compared,
one group in which the intervention takes place (e.g.
treatment with a certain drug) and another group
that remains ‘untouched’ (e.g. treatment with a
placebo).
 The two categories of intervention studies are:
 experimental studies and
 quasi-experimental studies
 Intervention (experimental) studies can
also be considered either therapeutic
or preventive.
85
Experimental studies
 An experimental design is a study design
that gives the most reliable proof for
causation.
 In an experimental study, individuals are
randomly allocated to at least two groups.
 One group is subject to an intervention,
or experiment, while the other group(s) is
not.
 The outcome of the intervention (effect
of the intervention on the dependent
variable/problem) is obtained by
comparing the two groups.
86
Quasi-experimental studies
 In a quasi-experimental study, one
characteristic of a true experiment is
missing, either randomization or the use of a
separate control group.
 A quasi-experimental study, however, always
includes the manipulation of an independent
variable which is the intervention.
 This quasi-experimental design is called the
‘non-equivalent control group design’
because the subjects in the two groups
(study and control groups) have not been
randomly assigned.)
87
 Therapeutic trials are conducted among
patients with a particular disease to
determine the ability of an agent or
procedure to diminish symptoms, prevent
recurrence, or decrease risk of death
from that disease.
 A preventive trial (community trial)
involves the evaluation of whether an
agent or procedure reduces the risk of
developing disease among those free from
that condition at enrolment.
◦ Thus, preventive trials can be conducted
among individuals at usual risk (e.g. vaccine
trials)
88
 A particular research question may be
addressed using different approaches.
 The choice of study design for investigation
is influenced by:
◦ Particular features of the exposure and disease.
◦ Logistic considerations of available resources.
◦ Results from previous studies and gaps in
knowledge that remain to be filled.
◦ Ingenuity and creativity of the researcher

89
Summary

90
 Descriptive studies
Examine patterns of disease, frequency of disease

Analytical studies
Studies of suspected causes of diseases,
predisposing factors, etc.

Experimental studies
Compare treatment modalities, preventive
modalities, causative factors
• therapeutic trials
• preventive trials
91
Hierarchy of Study Design
Study Designs
 Cohort Studies
Disease
People Exposed No disease
Population without
disease Not Disease
exposed
No disease
Study population
 The population under consideration
should be clearly and explicitly defined in
terms of place, time, and other relevant
criteria.
 If the study population comprises cases of
a disease the procedures to be used for
case identification should be stated.
 If controls are to be chosen their method
of selection should be stated.
95
 Often the investigator will have implicitly
chosen his study population when he
defined the topic of his investigation, by
reason of his interest in a specific
community or a specific health program.
 In an analytic survey or an experiment is
being planned, the investigator may
require purposively to select a study
population.
 In so doing he must consider questions of
appropriateness and practicability.
 The appropriateness of the study
population refers to its suitability for the
attainment of the objectives of the study.
96
 The selection of study population on the basis
of suitability usually affects the validity of
subsequent generalizations from the findings.
 Volunteer populations: Persons who volunteer
to enter a study may differ in many respects
from those who do not so volunteer, and
therefore the findings in a volunteer population
do not necessarily apply to the population at
large.
 Hospital or clinic populations: Persons
receiving medical care are obviously not
representative of the general population from
which they have come from.
◦ That is, persons treated in hospital for a certain
disease may differ from those patients with the
same disease but not receiving care for it.
97
Practical questions such as the following could also arise.

◦ Is the proposed population the one that

would give the required information?
◦ Will the population cooperate to participate
in the study, or will it be a 'resistant' one?
◦ If it is proposed to study patients with a
specific disease, will it be possible to identify
enough cases to yield useful conclusions?
◦ If a long term 'follow up' study is planned, is
the population so mobile that it may be
difficult to maintain contact with the subjects?
 A preliminary exploratory study may sometimes be
required in order to answer such questions.
98
Definitions of Variables
 Operationalizing variables by choosing appropriate
indicators, e.g. level of knowledge
 Defining variables and indicators of variables
◦ For certain variables, it may not be possible to adequately
define the variable or the indicator immediately because
further information may be needed for this purpose.
 Dependent and independent variables
 Background variables
◦ In almost every study involving human subjects,
background variables, such as, age, sex, educational status,
monthly family income, marital status and religion will be
included.
 Confounding variable
 Avoid ambiguity
 Make the variables to be more measurable
 Scales of Measurement
99
Sampling
 What is sampling?
◦ Sampling involves the selection of a number of
study units from a defined study population.
 When taking a sample, we will be
confronted with the following questions:
a) What is the group of people from which we
want to draw a sample?
b) How many people do we need in our
sample?
c) How will these people be selected?
100
Definitions
 Target population (reference population):
Is that population about which an
investigator wishes to draw a conclusion.
 Study population (population sampled):
Population from which the sample actually
was drawn and about which a conclusion can
be made.
 Sampling unit: The unit of selection in the
sampling process.
◦ For example, in a sample of districts, the sampling
unit is a district; in a sample of persons, a person,
in a sample of hospitals, a hospital, etc.

101
 Study unit: The unit on which the
observations will be collected.
◦ For example, persons in a study of disease
prevalence, or households, in a study of family size.
◦ N.B. The sampling unit is not necessarily the same
as the study unit.
 Sample design: The scheme for selecting
the sampling units from the study population.
 Sampling frame: The list of units from
which the sample is to be selected.

102
Sampling methods
a) Non-probability sampling methods
 The sampling methods do not claim to be
representative of the entire population.
A. Convenience sampling:
B. Quota sampling:
C. Purposeful sampling strategies for
qualitative studies:

103
A. 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.
B. Quota sampling: is a method that insures that a
certain number of sample units from different
categories with specific characteristics appear in the
sample so that all these 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.
C. Purposeful sampling strategies for qualitative
studies: Qualitative research methods are typically
used when focusing on a limited number of
informants, whom we select strategically so that
their in-depth information will give optimal insight
into an issue about which little is known.
104
b) Probability sampling methods:
 We have to be sure that we can generalise the
findings obtained from a sample to the total study
population.
 They involve random selection procedures to
ensure that each unit of the sample is chosen on
the basis of chance.
 Every member of the population has an a
non zero chance of being selected.
A. Simple Random Sampling (SRS):
B. Systematic Sampling:
C. Stratified sampling:
D. Cluster sampling:

105
Simple Random Sampling (SRS):
 To select a simple random sample you need
to:
◦ Make a numbered list of all the units in the
population from which you want to draw a
sample.
◦ Each unit on the list should be numbered in
sequence from 1 to N (Where N is the Size of
the population).
◦ Decide on the size of the sample
◦ Select the required number of sampling units,
using a “lottery” method or a table of random
numbers.
106
Systematic Sampling:
 Systematic samples are obtained by numbering
each value in the population and then selecting the
kth value at regular intervals (for example, every
5th, 10th, etc.) from the sampling frame.
 Ideally we randomly select a number to tell us
where to start selecting individuals from the list.
 Systematic Sampling is usually less time
consuming and easier to perform than SRS.
 It provides a good approximation to SRS.
 Should not be used if there is any sort of cyclic
pattern in the ordering of the subjects on the list.

107
Stratified sampling:
 Random or systematic samples of a
predetermined size will then have to be
obtained from each group (stratum).
 Stratification may be needed if:
◦ We want to reduce the standard error, by gaining
control of the composition of the sample

108
Cluster sampling:
 The selection of groups of study units
(clusters) instead of the selection of study
units individually is called cluster sampling.
Clusters are often geographic units (e.g.
districts, villages) or organizational units
(e.g. clinics).
 is obtained by dividing the population into
sections or clusters and then selecting one
or more clusters and using all members in
the cluster(s) as the members of the
sample.
109
• If we select elements randomly from the
selected clusters, the design effect of the
sample mean will go down and the precession
of the sample mean will increase
• One way to measure the clustering effect is
with an intraclass correlation among element
values within a cluster, averaged across
clusters
• The intraclass correlation measures the
tendency for values of a variable within a
cluster to be correlated among themselves,
relative to values outside the cluster

110
Multi-Stage Sampling:
 This method is appropriate when the
population is large and widely scattered. The
number of stages of sampling is the number
of times a sampling procedure is carried out.
 The primary sampling unit (PSU) is the
sampling unit (or unit of selection in the
sampling procedure) in the first sampling
stage;
 The secondary sampling unit (SSU) is the
sampling unit in the second sampling
stage, etc.
111
Example:
 After selection of a sample of clusters (e.g.
household), further sampling of individuals
may be carried out within each household
selected.
◦ This constitutes two-stage sampling, with the PSU
being households and the SSU being individuals.
 Advantages: less costly, we only need to
draw up a list of individuals in the clusters
actually selected, and we can do that when
we arrive there.
 Disadvantage: less precise than SRS.

112
Sampling error (i.e., random error)

 Random error, the opposite of reliability

(i.e., Precision or repeatability), consists of
random deviations from the true value,
which can occur in any direction.
 Sampling error (random error) can be
minimized by increasing the size of the
sample.

113
Reliability (or precision):
 This refers to the repeatability of a
measure, i.e., the degree of closeness
between repeated measurement of the
same value.
 Reliability addresses the question, if the
same thing is measured several times, how
close are the measurements to each
other?

114
The sources of variation resulting in poor reliability include:

a) Variation in the characteristic of the subject

being measured. Example: blood pressure
b) The measuring instruments, e.g. questionnaires
c) The persons collecting the information
(observer variation)
 Inter-observer variation: differences between
observers in measuring the same observation
 Intra-observer variation: differences in
measuring the same observation by the same
observer on different occasions.

115
Non Sampling error (i.e., bias)
 Bias, consists of systematic deviations
from the true value, always in the same
direction.
 It is possible to eliminate or reduce the
non-sampling error (bias) by careful
design of the sampling procedure.
 Validity: This refers to the degree of
closeness between a measurement and
the true value of what is being measured.
 Validity addresses the question, how close
is the measured value to the true value?
116
Examples of bias in sampling include:

 Bias resulting from incompleteness of the

sampling frame:
◦ accessibility bias,
◦ Seasonability bias,
◦ self-reporting bias,
◦ volunteer bias,
◦ non-response bias etc.

117
 Non-response bias refers to failure to obtain
information on some of the subjects included
in the sample to be studied.
 It results in significant bias when the following
two situations are both fulfilled.
1. When non-respondents constitute a
significant proportion of the sample.
2. When non-respondents differ significantly
from respondents.
 The issue of non-response should be
considered during the planning stage of
the study:
 Non-response should be kept to a
minimum. E.g. below 15%
118
Methods that may help in maintaining non-response at
a low level could be:

 Training data collectors to initiate contact

with study subjects in a respectful way and
convince them about the importance of the
given study (this minimizes the refusal type
of non-response)
 Offering incentives to encourage
participation (this should be done by taking
account of the potential problems that may
arise in conducting future research)
 By making repeated attempts (at least 3
times) to contact study subjects who were
absent at the time of the initial visit.
119
 The number of non-responses
should be documented according to
type, so as to facilitate an
assessment of the extent of bias
introduced by non-response.
 As much information as possible
should be collected on non-
respondents, so as to see in what
ways they may differ from
respondents.

120
 Sample size determination
 In planning any investigation we must decide how many
people need to be studied in order to answer the
study objectives.
◦ If the study is too small we may fail to detect important
effects, or may estimate effects too imprecisely.
◦ If the study is too large then we will waste resources.
 In general, it is much better to increase the accuracy of
data collection (by improving the training of data
collectors and data collection tools) than to increase
the sample size after a certain point.
 The eventual sample size is usually a compromise
between what is desirable and what is feasible.
 The feasible sample size is determined by the
availability of resources.
 It is also important to remember that resources are
not only needed to collect the information, but also to
analyze it. 121
In order to calculate the required sample size, you
need to know the following facts:

a) The reasonable estimate of the key

proportion to be studied. If you cannot
guess the proportion, take it as 50%.
b) The degree of accuracy required. That is,
the allowed deviation from the true
proportion in the population as a whole.
It can be within 1% or 5%, etc.
c) The confidence level required, usually
specified as 95%.

122
d) The size of the population that the
sample is 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.

123
Estimating a proportion
 Estimate how big the proportion might be (P)
 Choose the margin of error you will allow in the estimate of
the proportion (say ± w)
 Choose the level of confidence that the proportion in the
whole population is indeed between (p-w) and (p+w).
◦ We can never be 100% sure.
◦ Do you want to be 95% sure?
 The minimum sample size required, for a very large
population (N>10,000) is:

• Example (Prevalence of diarrhoea)

p = 0.26 , w = 0.03 , Z = 1.96 ( i.e., for a 95% C.I.)

Thus, the study should include at least 822 subjects. 124

 If the above sample is to be taken from a
relatively small population (say N = 3000),
the required minimum sample will be
obtained from the above estimate by
making some adjustment.
 821.25 / (1+ (821.25/3000)) =
644.7 ≈ 645 subjects
 N.B. If you don’t have any
information about P, take it as 50%
and get the maximum value of PQ
which is 1/4 (i.e., 25%).

125
Estimating a mean
 The same approach is used but with SE = σ/√n
 The required (minimum) sample size for a very
large population is given by :

• Example: A health officer wishes to estimate the

mean serum cholesterol in a population of men.
From previous similar studies a standard deviation
of 40 mg/100ml was reported. If he is willing to
tolerate a marginal error of up to 5 mg/100ml in his
estimate, how many subjects should be included in
his study? (α =5%, two sided)
Ans: 246 persons
NB: can be estimated from previous similar
studies or could be obtained by conducting a small
pilot study.
126
Comparison of two proportions
(f(α,β))


 α = type I error (level of significance)

 β = type II error ( 1-β = power of the
study)
 power = the probability of getting a
significant result
 f (α,β) =10.5, when the power = 90% and
the level of significance = 5%
127
Comparison of two means (sample
size in each group)

(f(α,β))


 and are mean and variance of

group 1 respectively.
 and are mean and variance of
group 2 respectively.

128
Plan for data collection
 Why should you develop a plan for data
collection?
 A plan for data collection should be
developed so that:
◦ you will have a clear overview of what tasks have
to be carried out, who should perform them, and
the duration of these tasks;
◦ you can organise both human and material
resources for data collection in the most efficient
way; and
◦ you can minimise errors and delays which may
result from lack of planning (for example, the
population not being available or data forms
being misplaced).
129
Stages in the Data Collection Process

Three main stages can be distinguished:

 Stage 1: Permission to proceed
 Stage 2: Data collection
 Stage 3: Data handling

130
1. Stage 1: permission to proceed
 Consent must be obtained from the relevant
authorities, individuals and the community in
which the project is to be carried out. This may
involve organizing meetings at national or
 provincial level, at district and at village level. For
clinical studies this may also involve obtaining
written informed consent.
2. Stage 2: Data collection
 When collecting our data, we have to consider:
 Logistics: who will collect what, when and with
what resources
 Quality control

131
Logistics of data collection
WHO will collect WHAT data?
 When allocating tasks for data collection, it
is recommended that you first list them.
 Then you may identify who could best
implement each of the tasks.
 If it is clear beforehand that your research
team will not be able to carry out the entire
study by itself, you might plan to look for
research assistants to assist in relatively
simple but time-consuming tasks.

132
HOW LONG will it take to collect the data for
each component of the study?
 Step 1: Consider:
 The time required to reach the study area(s);
 The time required to locate the study units (persons,
groups, records); If you have to search for specific
informants (e.g., users or defaulters of a specific
service) it might take more time to locate informants
than to interview them.
 The number of visits required per study unit.
◦ For some studies it may be necessary to visit informants a
number of times, for example if the information needed is
sensitive and can only be collected after informants are
comfortable with the investigator or if observations have
to be made more than once (for example, follow-up of
pregnant mothers or malnourished children).
◦ Time needed for follow-up of non-respondents should
also be considered.

133
 Step 2: Calculate the number of
interviews that can be carried out per
person per day
 Step 3: Calculate the number of days
needed to carry out the interviews.
 Step 4: Calculate the time needed for
the other parts of the study, (for example,
10 days)
 Step 5: Determine how much time you
can devote to the study.

134
WHEN should the data be collected?
 The type of data to be collected and the
demands of the project will determine the
actual time needed for the data to be
collected.
 Consideration should be given to:
◦ availability of research team members and
research assistants,
◦ the appropriate season(s) to conduct the field
work (if the problem is season-related or
◦ if data collection would be difficult during certain
periods),
◦ accessibility and availability of the sampled
population, and
◦ public holidays and vacation periods.
135
Ensuring quality
 Measures to help ensure good quality of
data:
 Prepare a field work manual for the research
team as a whole, including:
 Guidelines on sampling procedures and what to do if
respondents are not available or refuse to co-operate,
 A clear explanation of the purpose and procedures of
the study which should be used to introduce each
interview, and
 Instruction sheets on how to ask certain questions and
how to record the answers.
 Select your research assistants, if required,
with care. Choose assistants that are:
 from the same educational level;
136
  knowledgeable concerning the topic and local
conditions;
 not the object of study themselves; and
 not biased concerning the topic (for example, health
staff are usually not the best possible interviewers for a
study on alternative health practices).
 Train research assistants carefully in all
topics covered in the field work manual as
well as in interview techniques and make
sure that all members of the research team
master interview techniques such as:
 asking questions in a neutral manner;
 not showing by words or expression what answers one
expects;
 not showing agreement, disagreement or surprise; and
 recording the answers precisely as they are provided,
without sifting or interpreting them.
137
 Pre-test research instruments and research
procedures with the whole research team,
including research assistants.
 Take care that research assistants are not
placed under too much stress (requiring too
many interviews a day; paying per interview
instead of per day).
 Arrange for on-going supervision of research
assistants. If, in case of a larger survey, special
supervisors have to be appointed, guidelines
should be developed for supervisory tasks.

138
 Devise methods to assure the quality of
data collected by all members of the
research team. For example, quality can
be assured by:
 requiring interviewers to check whether the
questionnaire is filled in completely before finishing
each interview;
 asking the supervisor to check at the end of each
day during the data collection period whether the
questionnaires are filled in completely and whether
the recorded information makes sense; and
 having the researchers review the data during the
data analysis stage to check whether data are
complete and consistent.
139
3. DATA HANDLING
 Once the data have been collected and
checked for completeness and accuracy, a
clear procedure should be developed for
handling and storing them.
 Decide if the questionnaires are to be
numbered; identify the person who will
be responsible for storing the data; and
how they are going to be stored.

140
Methods of data collection
 The choice of methods of data collection
is based on:
 The accuracy of information they will
yield
 Practical considerations, such as, the need
for personnel, time, equipment and other
facilities, in relation to what is available.

141
The use of documentary sources
 Clinical records and other personal records, death
certificates, published mortality statistics, census publications,
etc.
Advantages:
 Documents can provide ready made information relatively
easily
 The best means of studying past events.
Disadvantages:
 Problems of reliability and validity (because the information
is collected by a number of different persons who may have
used different definitions or methods of obtaining data).
 There is a possibility that errors may occur when the
information is extracted from the records. (This may be an
important source of unreliability if handwritings are difficult
to read.
 Since the records are maintained not for research purposes,
but for clinical, administrative or other ends, the information
required may not be recorded at all, or only partly recorded.
142
Interviews and self-administered
questionnaires
 A public health worker conducting interviews
may be armed with a checklist of topics, but may
not decide in advance precisely what questions he
will ask.
 If his approach is flexible; the content,
wording and order of his questions vary from
interview to interview.
 Hence, his interviews are relatively unstructured.
 On the other hand, if a more standardized
technique where the wording and order of the
questions being decided in advance is used, it may
take the form of a highly structured interview.
143
 Self-administered questionnaire: the
respondent reads the questions and fills in
the answers by himself (sometimes in the
presence of an interviewer who “stands
by” to give assistance if necessary.
 The use of self-administered questionnaires
is simpler and cheaper, such questionnaires
can be administered to many persons
simultaneously.

144
On the other hand, interviews have many advantages:
 A good interviewer can stimulate and maintain the respondents
interest the frank answering of questions.
 If anxiety is aroused (e.g., why am I being asked these questions?),
the interviewer can allay it.
 An interviewer can repeat questions which are not understood,
and give standardized explanations where necessary.
 An interviewer can ask “follow-up” or “probing” questions to
clarify a response.
 An interviewer can make observations during the interview; i.e.,,
note is taken not only of what the subject says but also how he
says it.
 While interviewing, a precaution should be taken not to influence
the responses; the interviewer should ask his questions in a
neutral manner.
 He should not show agreement, disagreement, or surprise,
and should record the respondent’s precise answers without
shifting or interpreting them.
145
Questionnaire Design
 In questionnaire design remember to:
a) Use familiar and appropriate language
b) Avoid abbreviations, double negatives, etc.
c) Avoid two elements to be collected through one
question
d) Pre-code the responses to facilitate data processing
e) Avoid embarrassing and painful questions
f) Watch out for ambiguous wording
g) Avoid language that suggests a response
h) Start with simpler questions
i) Ask the same question to all respondents
j) Provide other, or don’t know options where
appropriate
k) Provide the unit of measurement for continuous
variables (years, months, kgs, etc)
146
l) For open ended questions, provide
sufficient space for the response
m) Arrange questions in logical sequence
n) Group questions by topic, and place a few
sentences of transition between topics
o) Provide complete training for interviewers
p) Pretest the questionnaire on 20-50
respondents in actual field situation
q) Check all filled questionnaire at field level
r) Include “thank you” after the last question

147
Importance of combining different data-
collection techniques

 A skillful use of a combination of different

data-collection techniques can maximize
the quality of the data collected and
reduce the chance of bias.
 Flexible techniques, such as, loosely
structured interviews using open-ended
questions and focus group discussions are
called qualitative research
techniques.
◦ They produce qualitative information, which is
often recorded in narrative form.
148
 Structured questionnaires that enable the
researcher to quantify pre- or post-
categorized answers to questions are an
example of quantitative research
techniques.
◦ The answers to questions can be counted and
expressed numerically.
 Both qualitative and quantitative research
techniques are often used within a single
study.

149
Methods of collecting qualitative data
 The benefits of using these approaches include
richness of data and deeper insight into the
phenomena under study.
 Unlike quantitative data, raw qualitative data
cannot be analysed statistically.
 The data from qualitative studies often derives
from face-to-face interviews(individual
interviews), focus groups or observation and so
tends to be time consuming to collect.
 Samples are usually smaller than with quantitative
studies and are often locally based.
 Data analysis is also time consuming and
consequently expensive.

150
Conducting a focus group discussion

 Recruitment of participants:
 Physical arrangements:
 Preparation of a discussion guide:
 During the discussion: One of the members of
the research team should act as a "facilitator" for
the focus group. One should serve as "recorder."
 Functions of the facilitator:
 Introduce the session
 Encourage discussion
 Encourage involvement
 Listen carefully and move the discussion from topic to topic.
Subtly control the time allocated to various topics so as to
maintain interest.
 Take time at the end of the meeting to summarize, check for
agreement and thank the participants.
151
 Report writing in focus group discussions:
◦ Start with a description of the selection and
composition of the groups of participants and
a commentary on the group process, so the
reader can assess the validity of the reported
findings.

152
Bias in Information Collection
 Possible sources of bias during data collection:
1. Defective instruments, such as:
 Questionnaires with:
◦ fixed or closed questions on topics about which little is known
(often asking the ‘wrong things’);
◦ open-ended questions without guidelines on how to ask (or to
answer) them;
◦ vaguely phrased questions;
◦ ‘leading questions’ that cause the respondent to believe one
answer would be preferred over another; or
◦ questions placed in an illogical order.
 Weighing scales or other measuring equipment that are not
standardised.
 These sources of bias can be prevented by carefully planning
the data collection process and by pre-testing the data
collection tools.

153
2. Observer bias:
 Observer bias can easily occur when conducting
observations or utilizing loosely structured
group- or individual interviews.
 There is a risk that the data collector will only
see or hear things in which (s)he is interested or
will miss information that is critical to the
research.
 Observation protocols and guidelines for
conducting loosely structured interviews should
be prepared, and training and practice should be
provided to data collectors in using both these
tools.
 Moreover it is highly recommended that data
collectors work in pairs when using flexible
research techniques and discuss and interpret the
data immediately after collecting it.
154
3. Effect of the interview on the informant:
 The informant may mistrust the intention of the
interview and dodge certain questions or give
misleading answers.
 For example: in a survey on alcoholism you ask
school children: ‘Does your father sometimes get
drunk?’
 Many will probably deny that he does, even if it is
true.
 Such bias can be reduced by adequately
introducing the purpose of the study to
informants, by phrasing questions on sensitive
issues in a positive way, by taking sufficient time
for the interview, and by assuring informants that
the data collected will be confidential.
155
Information bias:
 Sometimes the information itself has weaknesses.
◦ Medical records may have many blanks or be
unreadable.
◦ This tells something about the quality of the data and
has to be recorded.
◦ For example, in a TB defaulter study the percentage of
defaulters with an incomplete or missing address
should be calculated.
 Another common information bias is due to gaps
in people’s memory; this is called memory or
recall bias.
◦ A mother may not remember all details of her child’s
last diarrhoea episode and of the treatment she gave
two or three months afterwards.
◦ For such common diseases it is advisable to limit the
period of recall, asking, for example, ‘Has your child
had diarrhoea over the past two weeks?’
156
Data quality checks at the time of the interview:

 To examine consistency of data, two or more

questions are asked at the beginning and these
same questions are asked at the end.
 This helps to find out their consistency in the
response.
 Repeat the question in another form to avoid
doubts
 Use strict supervision and checking on the spot
and re-interviewing
 For data completeness, check right at the end of
the interview
 Check for odd answers given

157
Confidentiality of information
 Should be stated right on the top of the
first page of the questionnaire
 If possible, use code numbers instead of
names
 The purpose of the study should be
explained at the beginning
 The respondent has the right not to be
interviewed

158
Plan for data processing and analysis
 Why is it necessary to prepare a plan for
processing and analysis of data?
◦ all the information (s)he needs has indeed been
collected, and in a standardized way;
◦ (s)he has not collected unnecessary data which
will never be analyzed.
 What should the plan include?
◦ Sorting data,
◦ Performing quality-control checks,
◦ Data processing, and
◦ Data analysis.
 categorising the data,
 coding, and
 summarising the data in data master sheets,
159
Data Processing
 Editing
 Coding
 Classification
 Tabulation
 Percentages

160
Data analysis – quantitative data

 Frequency counts
 Cross-tabulations
 Processing and analysis of qualitative
data

161
Analysis
 Univariate analysis: Measures of central
tendency and measure of dispersion
 Bivariate analysis : Measure of association
and causality
 Multivariate analysis : Simultaneous
analysis of more than two variables
 Index number
 Time series

162
Hypothesis Testing
 Null and Alternate Hypothesis
 The level of significance
 Decision rule or test of hypothesis
 Type I and Type II error
 Tow tailed and one tailed tests

163
Results and discussion

164
 Brief Interpretation and discussion of the
results
◦ Descriptive statistics
◦ Inferential statistics
◦ Significant or not significant related to
hypothesis
◦ Conform to findings in literature

165
Interpretation and Report Writing
 The technique of interpretation often involves the
following steps:
 Researcher must give reasonable explanations of
the relations which he has found and he must
interpret the lines of relationship in terms of the
underlying processes and must try to find out the
thread of uniformity that lies under the surface
layer of his diversified research findings.
 Extraneous information, if collected during the
study, must be considered while interpreting the
final results of research study, for it may prove to
be a key factor in understanding the problem
under consideration.

166
 It is advisable, before embarking upon final
interpretation, to consult someone having
insight into the study and who is frank and
honest and will not hesitate to point out
omissions and errors in logical
argumentation.
 Researcher must accomplish the task of
interpretation only after considering all
relevant factors affecting the problem to
avoid false generalization. He must be in no
hurry while interpreting results, for quite
often the conclusions, which appear to be all
right at the beginning, may not at all be
accurate.

167
 STEPS IN WRITING REPORT
 The usual steps involved in writing report are:
◦ logical analysis of the subject-matter;
◦ preparation of the final outline;
◦ preparation of the rough draft;
◦ rewriting and polishing;
◦ preparation of the final bibliography; and
◦ writing the final draft.

168
Conclusion and Recommendations

169
 Implication of research findings
◦ Theoretical implication
◦ Practical implication
◦ Policy implication
• Recommendation for future
research
• Limitations
• Conclusions should follow logically
from the discussion on the findings.

170
Conclusions
 After analyzing the data and determining whether
to reject the null hypothesis, the researcher is
now in a position to draw some conclusions
about the results of the study.
 For example, if the researcher rejected the null
hypothesis, the researcher can conclude that the
phenomenon being studied had an effect a
statistically significant effect, to be more precise.
 It is important that researchers make only those
conclusions that can be supported by the data
analyses.
 Going beyond the data is a cardinal sin that
researchers must be careful to avoid.

171
Ethical Clearance or Ethics
statement

172
Why is Research Ethics
Important?
It is a reflection of respect for those who
‘take part’ in research
 It ensures no unreasonable, unsafe or
thoughtless demands are made by
researchers
 It ensures sufficient knowledge is shared
by all concerned
 It has become the norm as an
expectation for research activity
173
What Projects Need Ethical
Approval?
 Human participants
 Use of the ‘products’ of human
participants
 Animal participants
 Work that potentially impacts on human
participants
 Where ethical approval is deemed
unnecessary a disclaimer may be signed by
researcher (and supervisor)
174
Key Ethical Issues
 Informed Consent - special consideration for minors
 Deception
 Providing false information to the participant about the nature
and/or purpose of the study
 Need for debriefing
 Debriefing is an interview with the research participant
providing an opportunity for the experimenter to reveal
deceptive aspects of the study and for the participant to have
any questions about the study answered.
 Right to withdraw
 Participants must be informed that they are free to withdraw
from the study at any time without penalty.
 Confidentiality
 Safety and risk

175
Paraphrase!!!
176
WORK PLAN AND BUDGET
Work Plan
 It may include:
◦ The tasks to be performed;
◦ When and where the tasks will be performed;
and
◦ Who will perform the tasks and the time each
person will spend on them.

177
Budget
 Why do we need to design a budget?
◦ A detailed budget will help you to identify
which resources are already locally available
and which additional resources may be
required.
◦ The process of budget design will encourage
you to consider aspects of the work plan you
have not thought about before and will serve
as a useful reminder of activities planned, as
your research gets underway.

178
 MAJOR COMPONENTS AND
OUTLINE OF THE DIFFERENT
PHASES IN A RESEARCH
PROCESS

179
Summary of the major components
of a research proposal
 Title and cover page
 Abstract:
 Table of contents:
 Introduction
 Statement of the research problem
 State of knowledge: knowledge pertinent to
subject under study
◦ Local data/knowledge
◦ Literature review
 Significance of the proposed work
 Objective of the study
180
 Materials and methods
◦ Type of study (study design)
◦ Study population
◦ Type of data
◦ Inclusion/ exclusion criteria
◦ Sampling procedure, and sample size and power
calculation.
◦ Data collection and management
◦ Data analysis
 Ethical considerations:
 Pretest or pilot study:
 Work plan (project management)
 Budget
 References
 Appendices: -
181
Writing a research
report

182
 Title and cover page
 Abstract (Summary)
 Acknowledgements
 Table of contents
 List of tables, figures
 List of abbreviations (optional)
 Introduction
 Objectives

183
 Methods
◦ the study type;
◦ major study themes or variables (a more
detailed list of variables on which data were
◦ collected may be annexed);
◦ the study population(s), sampling method(s)
and the size of the sample(s);
◦ data-collection techniques used for the
different study populations;
◦ how the data were collected and by whom;
◦ procedures used for data analysis, including
statistical tests (if applicable).
184
 Results
◦ Findings should be presented
◦ Tables and graphs could be used (should be well titled and captioned
◦ The tables should be well constructed, and without anomalies such as
percentages which do not add up to 100 percent
◦ Avoid too many decimal places
◦ Graphs should clarify and not complicate, and care should be taken that
they do not mislead
◦ If appropriate statistical tests are used, the results should be included. P-
values alone are not very helpful. Confidence intervals and the type of
tests used should be indicated.
 Discussion
 Conclusions and recommendations
◦ policy-makers,
◦ health and health-related managers at district or lower level,
◦ health and health-related staff who could implement the activities,
◦ potential clients, and
◦ the community at large.
 References
 Annexes or appendices

185
186