Research Methodology

Ahmed Ali, Professor of Public Health and Epidemiology

School of Public health
College of health Sciences
Addis Ababa University
July, 2024

1
 Research Methodology
Course outline
• Variables (independent, dependant )
• Operational definitions and measurements
• Data collection techniques
• Questionnaire design and pre-testing

2
Variables of the study

• Variable is a measurable characteristic of a

person, object or phenomenon, which can
take on different values
• Identify the:
• Independent variable (exposure, intervention…)
• Dependent variable (outcome)

3
 Operational definitions
• 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

4
 Data collection and Management

Learning objectives :
• At the end of this lesson, learners will be able
to:
– Understand data collection techniques
– Develop data collection tools
– Pre-test data collection tools
– Amend data collection instruments
– Conduct data collection

5
 Data collection and Management

Describe your:
• Data collection techniques and tools
• Where will the information come from (data
sources)
• Who will collect the data?
• Who will supervise the data collection?
• How long will the data collection take ?

6
 What is Data Collection?
• It is the process by which the researcher
collects the information needed to answer the
research problem

• The task of data collection begins after a

research problem has been defined and
research design selected.

7
 Data collection…
• In collecting data, the researcher must decide:
– Which data to collect?
– How to collect the data?
– Who will collect the data?
– When to collect the data?

8
 Methods of Data Collection
Essentially Two Types:
• Primary Data: are those which are collected
for the first time and are original in character.

• Secondary Data: are those which have

already been collected by someone else and
made readily available for researchers to use
for their own research.

9
Common Data Collection Techniques

1. Interviews
– Face-to-face
– Telephone interviews
2. Self-administered questionnaire
– In person
– Postal or mail method
– Web based
3. Using available information
– Medical record review
– Desk review
10
 Data collection methods…

• The selection of a method for collecting

information depends on the :
– Resources available
– Credibility
– Analysis and reporting
– Resources
– Skill of data collectors

11
 1. Interviews

Interviews consist of oral questions by the

interviewer and oral responses by research
participants.

12
Types of interviews

Mode of interview
– Face to face interview
– Telephone interview
Flexibility
– Structured
– Semi structured
– Unstructured

13
 Structured Interviews

• A structured interview is a type of interview

in which the interviewer asks a particular set
of predetermined questions.

• In structured interviews, questions are

planned and created in advance, which means
that all respondents are asked the same
questions in the same order

14
 Unstructured interview

• An unstructured interview is a type of

interview in which the interviewer asks
questions that are not prepared in advance.

• In unstructured interviews, questions arise

spontaneously in a free-flowing conversation,
which means that different respondents are
asked different questions.

15
 Semi-structured interview

• A semi-structured interview is a type of

interview in which the interviewer asks only a
few predetermined questions, while the rest
of the questions are not planned in advance

• In semi-structured interviews, some questions

are predetermined ,while others arise
spontaneously in a free-flowing conversation.

16
Advantage and Disadvantage of Interviewing

Advantage
– Interview is more appropriate for complex situations
– Useful to collect in-depth information
– Information can be supplemented
– Questions can be explained
– High response rate
– More complete answer
– Appropriate for illiterates
Disadvantage
– Interviewing is time consuming and expensive
– The quality of data depends upon the quality of the interviewer
– The quality of data may vary when many interviewers are used
– The researcher may introduce his/her bias
– Small scale study
– Problem of anonymity
17
 Methods of conducting Interview

• A personal interview involves a lot of

preparation.
• Generally a personal interview should go
through the following five/5 stages:
1. Rapport Building
2. Introduction
3. Probing
4. Recording
5. Closing
18
 Methods of conducting Interview
1. Rapport Building
– Interviewer should increase the receptiveness of the respondent
by making him/her believe that his/her opinions are very useful
to the research, and is going to be a pleasure rather than an
ordeal.

2. Introduction
– An introduction involves the interviewer identifying him/her
self by giving him/her name, purpose and sponsorship if any.
– An introductory letter goes a long way in conveying the study’s
legitimacy.

19
 Methods of conducting Interview…
3. Probing
– Probing is the technique of encouraging the respondents to answer
completely, freely and relevantly.

4. Recording
– The interviewer can either write the response at the time of interview or
after the interview.
– In certain cases, where the respondent allows for it, audio or visual aids
can be used to record answers.

5. Closing
– After the interview, interviewer should thank the respondent and once
again assure him /her about the worth of his /her answers and its
confidentiality.
20
2. Self-administered questionnaire (SAQ)
• A SAQ refers to a questionnaire that has been designed
specifically to be completed by a respondent without an
interviewer
• Traditionally the SAQ has been distributed by mail or in person
to large groups, but now SAQs are being used extensively for
Web surveys.
• Since the SAQ is completed without on-going feedback from a
trained interviewer, special care must be taken in how the
questions are worded as well as how the questionnaire is
formatted in order to avoid measurement error.

21
SAQ…

A written questionnaire can be administered in

different ways, for example:
– Sending questionnaires by mail with clear
instructions on how to answer the questions and
requests for mailed responses;
– Gathering all or part of the respondents in one place
at one time, giving oral or written instructions, and
letting the respondents fill out the questionnaires; or
– Hand-delivering questionnaires to respondents and
collecting them later.
22
 Advantages of Self-administered
Questionnaire
• Considerably low cost
• Ease in locating respondents
• Saving time
• Respondent’s convenience
• Greater anonymity
• Honest response
• Less chance of biasing error

23
 Disadvantages of Self-administered
Questionnaire
• Low response rate
• Inflexibility
• Reasons for refusal not known
• No control over the sequence
• No control over the environment
• High incomplete response
• Cannot record spontaneous answers
• No way to supplement the answers
• No way to check the correct identity of respondents
24
Improving Response Rates in SAQ-Mail
method
• Follow-up through repeated reminders
• Prior notification
• Return envelopes: send paid self-addressed and
stamped envelope

25
 3. Secondary Data
• Secondary data are data that have been already
collected by and readily available from other
sources.

• Since the researcher does not collect the data, it's

important to become familiar with the data set:
– who the population of study was
– how the data were collected
– what the response categories were for each question
and more.
26
 Secondary data
Advantages
– Ease of access
– Time saving
– Inexpensive—government data are often free
– Requires no access to subjects
– Longitudinal analysis-the study spans over a long period of time

Disadvantages
– Data not consistent with needs
– Inappropriate units of measurement
– Data might be out of date
– No control over data quality
– Incomplete data
– Disorganized storage
27
 Sources of secondary data
• Examples of sources of secondary data that
are commonly used in epidemiological studies
include:
– population census records
– surveys of individuals and households (eg. DHS)
– Information collected by Health facilities (HMIS)
– patient medical records
– disease registries
– Vital registries (birth and death certificates)
28
 Questionnaire Development
• A questionnaire is a research instrument consisting of a series
of questions for the purpose of gathering information from
respondents.
• The design of questionnaires needs clear aims and objectives,
a selection of items that need to be translated into questions,
and a logical order.
• A well-designed questionnaire facilitates the respondents to
provide complete and accurate information.

29
Steps in Questionnaire Development

1. Decide on the information required.

– what are the things one needs to know from the respondent in order to meet the
survey's objectives?
– What are the specific research questions?
– What are hypotheses?
• List variables that you should measure
2. Define the target respondents.
– in designing the questionnaire we must take into account factors, such as the age,
education, etc. of the target respondents
3. Choose the method(s) of reaching your target respondents.
– the method of contact will influence not only the questions the researcher is able to
ask, but also the phrasing of those questions
4. Decide on content.
– One of the main and most difficult questions researchers should always ask
themselves is “do we really require the answer of this question for our study aims?”.
If there is no good justification for it, the question should be left out.
30
Steps in Questionnaire Development

5. Develop the question wording.

– Formulate one or more questions that will provide the information
needed for each variable
– Questions should be clearly worded and response options clearly
identified
– Consider requirements for effective questions
6. Put questions into a meaningful order
– Questions should flow in some kind of order, so that one leads easily and
naturally to the next
– Opening questions should be easy to answer and not in any way
threatening to the respondents
– Questions that are of special importance should, if possible, be included
in the earlier part of the questionnaire
– Sensitive questions should be raised last
31
 Steps in Questionnaire Development

7. Format the questionnaire

– The clarity of questionnaire presentation can also
help to improve the ease with which interviewers
or respondents are able to complete a
questionnaire
– Allocating sufficient space for answers
– Consider spacing., coding, skipping
8. Pre-test the questionnaire
9. Develop the final survey form.
32
Use existing questionnaires
– As an inspiration
– Don´t need to re-invent the wheel
– Have been tested
– BUT: adapt to present situation!
• Questionnaire needs to be adapted to study population
– occupation
– education
– ethnic group
– Language
– sensitive issues

33
 Types of survey questions

Closed ended questions (Single or Multiple

response )
– They allow your respondents to select one or
more options from a list of answers that you
define

34
 Rating scales

• In rating scale questions (sometimes referred to as ordinal

questions), the question displays a scale of answer options
from any range (0 to 100, 1 to 10, etc.).
• The respondent selects the number that most accurately
represents their response.
Eg. On a scale of 0-10 how do you rate the severity of your
pain?

35
 Likert scale
• Likert scale questions are the “do you agree or
disagree” questions you often see in surveys, and
are used to measure respondents’ opinions and
feelings
• Likert scales should be symmetrical and balanced.
– they should contain equal numbers of positive and
negative responses within the distance between each
item being the same.
• Always include word labels not just numbers to
identify what each point on the scale means.
36
Common Likert scales:

37
 Open-ended
• Open-ended survey questions require respondents to type
their answer into a comment box and don’t provide specific
pre-set answer options.
• Responses are then viewed individually or by text analysis
tools.
• Do you have any other comments. Questions, or concerns?

38
 Requirements of questions
Be clear, specific, and direct
Vague: What is your income?
– For what time period? For just the respondent or the entire household?
Before or after taxes?
Specific: What was your household’s yearly income before taxes in 2016?

Ask only one question at a time

– Each question should focus on a single item or concept. This generally
means that questions should have one subject and verb.
– Double-barrel questions ask a respondent to evaluate more than one
thing in a question yet only allow for a single response.

Ex. Do you take your child to a doctor when he/she has cold or diarrheal?

39
 Requirements of questions…
Avoid bias and leading words
– A biased question will lead participants in the direction of a
particular answer.
Biased: We think this lesson on Survey Question Writing is very helpful.
How helpful do you think this lesson is?

Unbiased: What do you think of this lesson on Survey Question Writing?

Keep the survey short and don’t be greedy!

• Don’t waste people’s time–only ask for what you really
need.
40
 Requirements of questions…
Present all the possibilities
• The number of answers should be kept relatively small but include all the possible choices
• All respondents need to be able to find an answer that fits their situation
• If there could be a situation where none of the answers apply, provide the option to select
“don’t know,” “not applicable” or “prefer not to answer” for sensitive questions.
Incomplete and Unbalanced:
– Very Important
– Moderately important
– Slightly important
What if it is not important at all? Or not even applicable to the participant?
Complete and Balanced:
– Extremely important
– Very important
– Moderately important
– Slightly important
– Not at all important
– Not applicable

41
 Requirements of questions …
Keep answers mutually exclusive
• If a participant can only select one response ,
each answer should be distinct and not cross-
over.
• For example, options might be 0-5 or 6-10
rather than 0-5 or 5-10. Having the “5” in both
answers makes them not mutually exclusive

42
 Pre-testing questionnaire
Helps to answer :
– Do respondents understand the questions?
– Are there any difficulties?
– Are there any sensitive questions?
– Is the question order appropriate?
– Does the researcher understand the respondent's
response?

43
 Pre-testing
• Refers to the testing of the questionnaire on a small sample of
respondents(5-10%) to identify and eliminate potential
problems.
• A questionnaire should not be used in the field survey without
adequate pretesting.
• All aspects of the questionnaire should be tested, including
question content, wording, sequence, form and layout,
question difficulty, and instructions.
• The respondents for the pre-test and for the actual survey
should be drawn from the same population.
• Pre-tests are best done by personal interviews, even if the
actual survey is to be conducted by mail, telephone, or
electronic means, since interviewers can observe respondents'
reactions and attitudes. 44
 Structure of a questionnaire

1. Introduction- cover letter

– Identify the sponsoring organization
– Explain the purpose of the study
– State how long it take to complete
– The sample design - to indicate how the respondent was chosen
– How you assure confidentiality of information, making clear that there are no wrong or right
answers. Honest answers are also requested
– What will happen to the results
– A contact person /return address
– Sample-Survey-Cover-Letter.pdf

2. Respondent Identification - (code, HH.No., ID.No., Card No, Registration No.)

3. Body- Instructions and Questions
4. Conclusion: “Thank you for taking the time to complete this survey 45
 Sample conclusion statement

Thank you for taking the time to complete this

survey. We truly value the information you have
provided. We will let you know the findings or you can
find the latest updates on the project here at this
website . If you have any comments on the survey or
the project, please leave a comment below.
Many thanks,
(Name of the Project)

46
 What makes a well designed questionnaire?

• Good appearance (easy for Basic Rules

the eye) • On first page
– Return address
• Short and simple
– Study title
• Relevant and logical • On all pages
• Identifier
⇒ High response
• Page numbers
⇒ Easier to collect
• Numbered questions
to • Instructions (in bold or italic
summarize
to analyse

47