DATA

COLLECTION

Dr. Mohammed Hamed

RN, MBBS, FAIMER fellow, MHPE
University of Khartoum- faculty of medicine- EDC
staff.
 ILO’S

By the end of this session the participants

will be able to:

o Data collection tool

o Data collection techniques

o Variables: dependent/ independent

o Piloting

2
 MAIN COMPONENTS OF A
RESEARCH

• Preparing a research proposal

• Fieldwork (i.e., data collection)

• Analysing data and

• Preparing a research report (thesis)

• Get your work published (Journal article)

 Data
collection
The methodical process of
gathering specific information to
offer solutions to relevant
questions and to evaluate the
results

(Problem statement-
Research question,
Objectives)
DATA SOURCES
• Primary data:
• Researches

• Secondary:
• Previous researches
• Official statistics
• Mass media products
• Diaries
• Letters
• Government reports
• Web information
DATA COLLECTION TOOLS AND
TECHNIQUES

Tools Techniques
• Questionnaire • Interview/ self-
administered/
• Data collection form telephone interview/
• Checklist e-mail ….
• Likert scale • Desk review
• Observation
• Focus group
discussion guide • Examination
• Focus group
• In-depth interview discussion
guide • In-depth interview
DATA COLLECTION TECHNIQUES
AND TOOLS
Techniques
Tools
• Interview; self-
administered; telephone; • Questionnaire
e-mail; google form ….
 Desk review • Data collection form

 Observation • Checklist
 Examination

 Focus group
• Facilitator/
discussion Moderator guide
 In-depth interview
DATA COLLECTION TECHNIQUES
AND TOOLS
Techniques
Tools
• Interview; self-
administered; telephone; • Questionnaire
e-mail; google form …. Quantitative
 Desk review • Data Research
collection form

 Observation • Checklist
 Examination

 Focus group Qualitative

• Facilitator/
discussion Research
Moderator guide
 In-depth interview
 QUESTIONNAIRE DESIGN

1. Determine the questions to be asked

2. Select the question type and specify the

wording

3. Design the question sequence and the

overall questionnaire layout
 1. DETERMINE THE QUESTIONS TO BE
ASKED

• The objectives (E.g.: KAP)

• The issues/ main points for each

objective (eg prevention, diagnosis, or
treatment)

• The question focus (eg Knowledge score)

2.1 THE QUESTION TYPE AND WORDING

• Open vs. closed questions

• Single vs. multiple responses
• Ranking
• Rating
Closed-ended question Open-ended question

Did you know-how go to the How did you go to the

dermatology clinic? dermatology clinic?

Would you consider to advice What make you to advice

other patients to come to the other patients to come to the
to the dermatology clinic? to the dermatology clinic?
2.2 THE QUESTION TYPE AND WORDING

• Be concise and unambiguous

• Avoid double questions

• Avoid questions involving negatives

• Ask for the precise answers

• Avoid leading questions

3. Question sequence and the overall layout

Easy to difficult or vice User friendly

versa

Sensitive questions Suitable Length

Logical: KAP Ethical points

13
LIKERT
SCALE
WHAT IS LIKERT SCALE?
• It is the most widely used approach to scaling
responses in survey research…

• Respondents specify their level of agreement or

disagreement with statement on an agree-
disagree scale …

• The range captures the intensity of their feelings

for a given item

• The results of analysis of multiple items reveals

the pattern
THE FORMAT OF A TYPICAL FIVE-LEVEL
LIKERT ITEM

1. Strongly disagree
2. Disagree
3. Neither agree nor
disagree
4. Agree
5. Strongly agree
 Likert scale: Cons and pros
Advantages Limitations:
• Item analysis increases • Ties in ranks occur quite
the degree of frequently
homogeneity or • The response pattern of
internal consistency in an individual is not
the set of statements revealed
• A respondent is required
• Subjects generally find to answer all questions
on the scale
it easy to respond
•A problem of
interpretation arises
• No outside group of with this type of scale
judges is involved in • In this scale all
selecting statements statements of a
and giving values to universe are deemed to
them be of equal attitude
value
CHECKLIST
FOCUS
GROUP
DISCUSSION
(FGD)
WHY FGD?

• Clarifying and eliciting more details answer

• Behaviour

• Why questions
FGD: KEY POINTS
• Is the FGD the best way to address my research
question?
• Qualitative/ quantitative
• Limitations of FGD
• FGD guide

• I am inviting the right people?

• 6 -8 persons/ group
• Homogenous
• 3-4 FGDs (?saturation)

• What are you going to get them to talk about?

• General/ specific
• Theme/ Probing questions
• 40 – 90 minutes

• How are you going to analyse the discussion?

ANALYSIS OF FGD DATA
• Content analysis: frequency

• Thematic analysis: things

discussed

• Interpretative analysis: who said

what under which circumstances

• Discourse analysis: the language

used to describe?
THINGS TO THINK ABOUT IN ADVANCE
• Scheduling of the interview

• Location of the interview

• Who will lead the interview?

• How you will capture responses?

• How you will tackle the data analysis?

• How will you run the session?

IN-DEPTH
INTERVIEW
 TESTING THE TOOLS AND PILOTING
• A pilot study is a small scale
preliminary study conducted in order to evaluate
feasibility, duration, cost, adverse events, and
improve upon the study design prior to
performance of a full-scale research project

• Pretesting tools help you identify questions that

don't make sense to participants, or problems with
the questionnaire that might lead to biased answers
 PREPARATION TO FIELD WORK
• Finalize the tools after pretesting

• Select and train data collectors, field supervisors

• Prepare all needed equipment, stationeries if any

• Secure needed logistics

• Prepare/sensitize the study area and population

DURING FIELD WORK

• Ensure data
• Quality:
• Completeness
• Consistency
• Timely transfer for analysis
AFTER FIELD WORK

• Ensure data preservation

• Plan for data sharing and dissemination
ELECTRONIC DATA COLLECTION

?
VARIABLES

1. Independent Variables (IVs)

• Definition: These are variables that are manipulated or

categorized to observe their effect on dependent variables.

• Example: In a study on the effects of a new drug, the

independent variable could be the dosage level of the drug

administered.
VARIABLES

• 2. Dependent Variables (DVs)

• Definition: These are the outcomes or responses that are

measured to assess the effect of the independent variable.

• Example: In a study measuring the impact of a training

program on employees, the dependent variable could be
the improvement in performance scores post-training.
VARIABLES

3. Confounding Variables

• Definition: These are external variables that may

unintentionally influence the dependent variable and
potentially distort the observed relationship between the IV
and DV.

• Example: If researching the impact of a study method on

test scores, a confounding variable could be the students’
natural academic aptitude.
 RELIABILITY AND VALIDITY

• Reliability and validity are concepts used to

evaluate the quality of research.
• Reliability is about the consistency of a
measure (Cronbach's alpha)
• Validity is about the accuracy of a
measure (Experts view)
RELIABILITY VS VALIDITY
• Reliability and validity are concepts used to evaluate
how well a method measures something….
• Quality of research

• Reliability refers to the consistency of a measure

(whether the results can be reproduced under the same
conditions).
• Cronbach's alpha

• Validity refers to the accuracy of a measure (whether the

results really do represent what they are supposed to
measure).
• Experts view
 INTERNAL AND EXTERNAL VALIDITY
• Validity: How sound is the research methods of
the study?
• Internal validity
• Defined as the extent to which the observed
results represent the truth in the sample and,
thus, are not due to methodological errors …
• The degree to which the relationship between
the dependent variable and an independent
variable can be established?
• External validity
• Refers to the extent to which the results of a
study are generalizable to patients in our daily
practice, especially for the population that the
sample is thought to represent Generalization
of findings to other population and settings.
 THREATS TO INTERNAL VALIDITY

• Selection bias
• Sample size
• Confounding
• History
• Maturation
• Instrumental
• Testing/ practice effect
• Attrition/ mortality
THREATS TO EXTERNAL VALIDITY

• Participants characteristics

• Setting

• Timing
QUALITATIVE
RESEARCH

41
 QUALITATIVE RESEARCH…

 Allows the researcher to understand a problem or

phenomenon from the perspectives of the people it
involves

 Reveals a complete picture of a certain research issue

 Seeks to provide a rich understanding of a certain

research issue

 Researcher himself/ herself is the key research tool

42
Comparison of quantitative and qualitative
methods

QUALITATIVE QUANTITATIVE

Multiple realities Single reality

Reality is socially constructed Reality is objective

Reality is context interrelated Reality is context free

Holistic Reductionistic

Reasoning is inductive Reasoning is deductive and

inductive
Discovery of meaning is the basis Cause-and-effect relationships are
of knowledge the bases of knowledge
Develops theory Tests theory

43
Comparison of quantitative and qualitative
methods (continued)

QUALITATIVE QUANTITATIVE

Meaning of concepts Measurement of variables

Process oriented Outcome oriented

Control unimportant Control important

Rich descriptions Precise measurement of variables

Basic element of analysis is words Basic element of analysis is numbers

Uniqueness Generalization

Trustworthiness of findings Control of error

44
QUALITATIVE TRADITIONS OF INQUIRY…

• Biography
• Historical research
• Phenomenology
• Grounded theory
• Ethnography
• Ethnology
• Case study
• Symbolic interaction

45
STEPS IN QUALITATIVE STUDY

1. General research question

2. Select relevant site(s) and subjects
3. Collection of relevant data
4. Interpretation of data
5. Conceptual and theoretical work
6. Tighter specification of the research
question
7. Collection of further data
8. Conceptual and theoretical work
9. Write up findings
46
47
ETHICAL CONSIDERATIONS

• Mutual respect and trust

(prolonged interaction)
• Respect for social and cultural contexts
• Voluntary participation
• Informed consent
• Beneficence – doing good for others
and preventing harm
• Confidentiality

48
DETERMINING A SAMPLE

• In qualitative research, the researcher needs

to define and select a sample…

• Even if it were possible, it is not necessary to

collect data from everyone in a community…

• The research objectives and the

characteristics of the study population
determine which and how many people to
select…

49
SAMPLE SIZE
• Usually smaller than quantitative study.

• Two general guidelines: the number of

participants is sufficient when…
• The extent to which the selected participants
represent the range of potential participants in
the setting

• The point at which the data gathered begin to

be redundant (data saturation)

50
SAMPLING METHODS

• Non-probability sampling

• Three of the most common sampling

methods are:
• Purposive sampling
• Quota sampling
• Snowball sampling

51
TYPES OF DATA
• Written field notes
• Audio recordings of conversations
• Video recordings of activities
• Diary recordings of activities / thoughts
• Documents
• Depth information on:
• thoughts, views, interpretations
• priorities, importance
• processes, practices
• intended effects of actions
• feelings and experiences
52
DATA COLLECTION METHODS/ TECHNIQUES

• Three data collection strategies

(methods/ techniques):
1. Participant observation
2. In-depth interviews
3. Focus group interviews

• Qualitative researchers may combine

more than one method

53
DATA ANALYSIS

• Manual/ software

• Open coding

• Systematic coding

• Affinity diagramming

54
REPORTING RESULTS

• Find the main themes

• Use quotes / scenarios to represent them
• Include counts for codes (optional)

55
VALIDITY, RELIABILITY
AND
GENERALIZABILITY IN
QUALITATIVE
RESEARCH

56
THREATS TO VALIDITY

• Observer bias
• Invalid information resulting from the perspective the researcher
brings to the study and imposes upon it
• e.g., studying one’s own culture

• Observer effects
• The impact of the observer’s participation on the setting or the
participants being studied
• e.g., people may do things differently

57
 STRATEGIES TO ENHANCE VALIDITY
• Intensive, long term involvement: repeated observation and interviews

• Rich data: full and detailed descriptions

• Respondent validation: ask them if the reporting is correct

• Intervention: interact with them and see how behavior changes

• Searching for negative cases and alternative explanations

• Triangulation: collect data from a variety of settings and methods

• Quasi-statistics: e.g., frequency counts of the argument

• Comparison: multicase, multisite studies

58
RELIABILITY
• It is a quantitative measure and the concept is
irrelevant in qualitative research….

• However, to test a qualitative study for

reliability, you need to convert data into
relevant numbers and determine efficacy based
on the results…

59
Generalization
• Generalizability allows us to have
expectations about the future…

• A limitation of qualitative research is that

there is seldom justification for generalizing
the findings of a particular study...

• Due to this problem, replication of

qualitative studies becomes more
important than for quantitative studies…
60
THANK
YOU