Test selection in psychological assessment is guided, both explicitly and implicitly, by how informative tests are with regard to a trait of interest. Most existing formulations of test information are sensitive to subpopulation variation, with the result that test information will vary from sample to sample. Recently, measures of test information have been developed that quantify the potential informativeness of the test. These indices are defined by the properties of the test, as distinct from the properties of the sample or examinee. As of yet, however, measures of potential information have been developed only for unidimensional tests. In practice, psychological tests are often multidimensional. Furthermore, multidimensional tests are often used to estimate one specific trait among many. This study develops measures of potential test information for multidimensional tests, as well as measures of marginal potential test information---test information with regard to one trait within a multidimensional test. In Study 1, the performance of the metrics was tested in data simulated from unidimensional, first-order multidimensional, second-order, and bifactor models. In Study 2, measures of marginal and multidimensional potential test information are applied to a set of neuropsychological data collected as part of Rush University's Memory and Aging Project. In simulated data, marginal and multidimensional potential test information were sensitive to the changing dimensionality of the test. In observed neuropsychological data, five traits were identified. Verbal abilities were most closely correlated with probable dementia. Both indices of marginal potential test information identify the Mini Mental Status Exam as the best measure of that trait. More broadly, greater marginal potential test information calculated with regard to verbal abilities was associated with greater criterion validity. These measures allow for the direct comparison of two multidimensional tests that assess the same trait, facilitating test selection and improving the precision and validity of psychological assessment.
Potential test information for multidimensional tests
Abstract
Details
- Title: Subtitle
- Potential test information for multidimensional tests
- Creators
- Katherine Grace Jonas - University of Iowa
- Contributors
- Kristian E. Markon (Advisor)Michael W. O'Hara (Advisor)Daniel Tranel (Committee Member)Isaac T. Petersen (Committee Member)Mary Kathryn Cowles (Committee Member)
- Resource Type
- Dissertation
- Degree Awarded
- Doctor of Philosophy (PhD), University of Iowa
- Degree in
- Psychology
- Date degree season
- Summer 2017
- DOI
- 10.17077/etd.0aotewr6
- Publisher
- University of Iowa
- Number of pages
- vii, 81 pages
- Copyright
- Copyright © 2017 Katherine Grace Jonas
- Language
- English
- Date submitted
- 09/27/2017
- Description illustrations
- illustrations
- Description bibliographic
- Includes bibliographical references (pages 50-56).
- Public Abstract (ETD)
Most psychological tests measure more than one trait. For example, questions included on math tests are often written in verbal format ("how many eggs are in two dozen?") rather than numeric format (2 × 12 = ). An examinee’s response to the first question depends on both verbal skills and arithmetic skills. This characteristic may be a good or a bad thing, depending on the intended use of the test, and so it would be useful to distinguish how well a test measures one trait versus another. Currently, however, there are very few ways to do this.
A second complicating factor is that, by many metrics, the informativeness of a test will depend on the characteristics of the sample as well as the characteristics of the test. That is, if a test of depression is administered to a healthy, non-depressed sample, it will appear to be an unreliable test, even though it may function very well in a clinical setting.
This study develops measures of test information that resolve both problems: distinguishing test information for multiple traits, and doing so in a way that is robust to sample characteristics. The analyses demonstrate that the new measures are accurate in simulated data. And, in real data derived from a large battery of cognitive tests, the measures show how unreliable tests can still be valid and useful in the prediction of dementia. The proposed measures of test information will be useful in the development and selection of psychological tests.
- Academic Unit
- Psychological and Brain Sciences
- Record Identifier
- 9983776930102771