D-score booklet III
Tailoring tests to fit the occasion
1
Introduction
1.1
Measurement pyramid
1.2
Actual situation
1.3
Need for better instruments
1.4
Effect of proliferation
2
Criteria for better instruments
2.1
When is an instrument ‘better?’
2.2
Components of an instrument
2.3
Fixed instrument versus adaptive test
2.4
Assessment of instrument quality
3
Information
3.1
Item information by ability
3.2
Item information by age
3.3
Test information by ability
3.4
Test information by age
4
Item bank
4.1
Purpose of item bank
4.2
Information contained
4.3
\(D\)
-bank for child development milestones
5
Item selection
5.1
Administration mode
5.2
Preferred variant
5.3
Expercent pass
5.4
Content balancing
5.5
Age band
5.6
Precision
5.7
Item exposure limitation
6
Online instrument creation
6.1
Item selection
6.2
Fixed instrument
6.2.1
Item allocation
6.2.2
Age forms
6.2.3
Domain Representation
6.2.4
Reliability
6.3
Adaptive test
6.3.1
Domain representation
6.3.2
Adaptive test settings
6.3.3
Reliability
7
Application I: Population study
7.1
SDG 4.2.1 indicator
7.2
Formulation of requirements
7.3
Application in
dinstrument
7.4
Compare fixed instrument to adaptive test
8
Application II: Cohort study
8.1
Effect size for intervention effect
8.2
Formulation of requirements
8.3
Application in
dinstrument
8.4
Compare fixed instrument to adaptive test
9
Application III: Individual monitoring
9.1
Individual
\(D\)
-score trajectories
9.2
Definition of developmental delay
9.3
Formulation of requirements
9.4
Application in
dinstrument
9.5
Compare fixed instrument to adaptive test
10
Discussion
10.1
Potential of item bank for creating new instruments
10.2
Potential of adaptive testing
10.3
Limitations
10.4
Advantages
References
D-score booklet III
Chapter 2
Criteria for better instruments