By:
Dr. Sohail Saadat
Assistant Professor, Incharge
DIKIOHS-DUHS
Understand and appreciate data and
data collection methods
Have knowledge of different data
collection tools
Construct a questionnaire
Execute data collection
Data is existing information
/knowledge represented or coded
in some form suitable for better
usage or processing.
Data is a set of values of qualitative
or quantitative variables.
The task of data collection begins
after a research problem has been
defined and research design/plan
chalked out (Protocol).
The aims, study design and selected
population or sample will provide
information on both the type of data
and the frequency with which they
need to be collected
What is to be measured?
The principle aim of data collection is
to ensure data should be Valid ,
Reliable and unbiased.
Valid means that the
data measure
something that truly
exists accurately
Reliable means if
measurements are
taken at different
occasion the same
answer is obtained
Training and calibration of examiners
and recorders in the measures and
criteria is necessary:
assessments of the same observer at
different times - INTRA-OBSERVER
RELIABILITY
assessments of different observers
at the same time - INTER-OBSERVER
RELIABILITY
Unbiased: neither the
subject nor the examiner
influences the finding
Single blind Study:
subjects do not know
whether they are in the
treatment group or not.
Double blind study:
Neither the subject nor
the Researcher are
aware.
Systematically collect data from files,
documents, or real life (observation in the
field)
A form that specifies exactly what data you
want to collect
Example : WHO oral examination form
An instrument (form) to
collect answers to questions
collect factual data
gathers information or measures
A series of written questions/items in a
fixed, rational order
A well designed questionnaire:
Provides accurate and relevant information to your
research question
Minimises potential sources of bias
Will more likely be completed
It should be as simple and focused as possible
Can reach a large number of people relatively
easily and economically
Provide quantifiable answers
Relatively easy to analyse
Provides only limited insight into
problem
Limitedresponse allowed by questions
May be not the right questions are asked
Varying response
Misunderstanding/misinterpretation
Need to get it right first time
Hard to chase after missing data
Face to face By post
Telephone E-mail/Internet
Interviewer Self
-administrated -administrated
Postal Personal Phone Internet
questionnaire interview interview questionnair
e
Cost Low High Moderate Low
Data quality:
Response rate Low High Moderate Low
Respondent Low High High Low
motivation
Interviewer bias None Moderate Low None
Sample quality: Low, unless High Moderate Moderate,
high response to high, but
rate especially improving as
with internet
random access
digit dialling widens
Possible Short Very long Long Short
interview length:
Postal Personal Phone Internet
questionnair Interview interview questionnair
e e
Ability to None High High None
clarify and
probe
Anonymity High Low Low Low
Dependence High None None High
on
respondent’s
literacy:
Control of None High High Depends
context
depends
and question
order:
Advantages:
Cheap and easy to administer
Preserves confidentiality
Completed at respondent's convenience
No influence by interviewer/researcher
Disadvantages:
Low response rate
Questions can be misunderstood
No control by interviewer
Time and resouces loss
Advantages:
Participation by illiterate people
Clarification of ambiguity
Quick answers
Disadvantages:
Interviewer bias
Needs more resources
Only short questionnaires possible
Especially on telephone
Difficult for sensitive issues
Design questions:
Content of the questions
Format of the questions
Presentation and layout
Pilot and refine questionnaire
On first page
Return address
Study title in bold
On all pages
Numbered items
Page numbers
Directions in bold
Self-addressed envelope!!
Decide on order of items/questions
Easy difficult
General particular
Where to place sensitive questions?
Group questions by topic/ response options
Starting questions
Simple
Relevant to main subject
Non-offending
Neither demographic nor personal questions
Don’t put most important item last
Covering letter/ interview introduction
Who you are/ you work for
Why you are investigating
Where you obtained the respondent’s name
How and where you can be contacted
Guarantee of confidentiality
Length of interview (be honest)
Uusefulness of study should be clear
to all respondents
Ask for one information at a time
Do you own a dog or have frequent contacts
with dogs?
Yes
No
Do you often touch dogs?
Yes
No
vs.
How often did you touch a dog during the
past 3 months?
Once
Twice
Three times or more
Not at all
Don´t know
Are you a drunk?
Yes
No
vs.
How often have you consumed alcoholic
beverages during the past 6 months?
Daily
2-6 times/week
Once a week
Less than once a week
Don´t know
Did you smoke not less than a mean
amount
of 7 cigarettes/2 days from 2003 onwards?
Yes
No
vs.
Did you smoke an average of 2 pack of
cigarettes/week for the last 5 years?
Yes
No
Don´t know
The data must be relevant to the
research problem.
It should be collected through formal or
standardized research tools.
The data should be such as these can
be subjected to statistical treatment
easily.
The data should be accurate and
precise.
The data should be reliable and valid
The data should be complete in itself
and also comprehensive in nature.
THANK YOU