Documente Academic
Documente Profesional
Documente Cultură
AND
RELIABILITY OF
QUESTIONNAIRES
Dr. R. VENKITACHALAM
CONTENTS
Introduction
Steps in questionnaire designing
Validity
Concept of validity
Types of validity
Steps in questionnaire validation
Reliability
Types and measurement of reliability
Conclusion
References
INTRODUCTION
Questionnaire: Important method of data collection used
extensively
Advantages of questionnaire
Less expensive
Offers greater anonymity
Disadvantages
Application is limited
Response rate is low
Opportunities to clarify issues is lacking
Ideal requisites of a questionnaire:
Should be clear and easy to understand
Layout is easy to read and pleasant to eye
Sequence of questions easy to follow
Should be developed in an interactive style
Sensitive questions must be worded exactly
Degree to which the researcher has measured what he has set out to
measure (Smith, 1991)
Investigator
Readers of report
Experts in the field
Logic
Statistical tests
Logical thinking
Justification of each question in relation to objective of study
Validity
Face validity
Simply addresses whether a measuring instrument looks
valid
Not a validity in technical sense because it does not refer
to what is actually being measured rather what it appears
to measure
It has more to do with rapport and public relations than
with actual validity
Other aspects of content validity
Coverage of issue should be balanced
It is of two types:
Predictive validity
Concurrent validity
Predictive validity
If the test is used to predict future performance
CONCURRENT PREDICTIVE
What it Whether the test The ability of The ability of the The extent to
measures covers a the test to test to predict which the
representative estimate present future instrument
sample of the performance performance measures a
domains to be theoretical
measured construct
How it is Ask experts to Correlate Correlate Correlate
accomplished assess the test to performance on performance on performance on
establish that the the test with a the test with a the instrument
items are concurrent behaviour in with a
representative of behaviour future performance on
the outcome an established
instrument
Steps in
questionnaire
validation
FACE VALIDITY
Layout
Feasibility
and style
Clarity of wording
CONTENT VALIDITY
Two phases
Researcher: ConceptualizationPut
anditems/questions in a form
domain analysis that is testable
How do experts evaluate validity
Method 1: Average Congruency Percentage (ACP)
[Popham, 1978]
Two approaches:
S-CVI/UA – Universal agreement
S-CVI/Ave - Average
Which would be an effective measure here ??
S-CVI/UA or S-CVI/Ave
Which to follow?
Report both the values I-CVI and S-CVI rather than using
CVI as an acronym
Report the range of I-CVI values
Disadvantages
Practice effect (mainly for tests)
Too short intervals in between (effect of memory)
Some traits may change with time
Statistical calculation
Formula: r = Σ (x-x’)(y-y’)
√ Σ(x-x’)2 (y-y’)2
Cronbach’s alpha:
Another method of calculation using the formula:
R = k/k-1 (1-Σσ12/σy2)
k = total number of items in list
σ1 = variance of individual items
σy2 = variance of total test scores
Inter-rater reliability (Equivalence)
Used when a single event is measured simultaneously and
independently by two or more trained observers
R= Number of agreements
Number of agreements + Number of disagreements
Summary of Reliability
Validated questionnaire
It is one which has undergone a validation procedure to
show that it accurately measures what it aims to,
regardless of who responds, when they respond, and to
whom they respond or when self-administered and whose
reliability has also been examined thereby:
Polit DF, Cheryl Tatano Beck. The Content Validity Index: Are You Sure
You Know What’s Being Reported? Critique and Recommendations. Res
Nurs Health. 2006;29:489–97.