4. Criteria of a Good Test
1.Clarity of Learning Objectives
2.Practicality
3.Efficiency
4.Effectiveness
Introduction
5. What Is Test
Validity?
Validity
Does your test actually
measure what it is designed
to measure?
Reliability
Does your test yield
consistent results?
TRUTHFULNESS CONSISTENCY
6. Different Ways to Gauge Validity
1. Content-
related
2.Construct-
related
3. Criterion-
related
• Shows evidence that the test items adequately reflects
the test domain
• Usually results in high face validity
• Shows evidence that a test adequately captures the
concept (or construct) that it is designed to capture
• Shown via convergent & discriminant validation
techniques
• Shows that a test is able to predict the behavior that is
designed to predict
• Shown via concurrent & predictive validation
techniques
7. Content-related Validity
Content-related
Validity
• Shows evidence that the test items
adequately reflects the test domain-via
literature review, consulting subject matter
experts (SMEs)
GOAL:
To ensure that you comprehensively
cover/capture the test domain of interest
FACE
CONTENT
8. Criterion-related Validity
Criterion-related
Validity
• Shows that a test is able to predict the
behavior that it is designed to predict
GOAL:
To show that your test scores actually lead to
predicted behavioral outcomes either
now(concurrent) or in the future(predictive)
9. Construct-related Validity
Construct-related
Validity
• Shows evidence that a test adequately
captures the concept (or construct) that is
designed to capture
GOAL:
To show that your test correlates positively
(convergent) with similar tests and
negatively(discrimination) with dissimilar tests
DIVERGENT
CONVERGENT