Properties of a Resampling Validation Technique for Empirically Scoring Psychological Assessments
Mead, Alan David
This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.
Permalink
https://hdl.handle.net/2142/82307
Description
Title
Properties of a Resampling Validation Technique for Empirically Scoring Psychological Assessments
Author(s)
Mead, Alan David
Issue Date
2000
Doctoral Committee Chair(s)
Drasgow, Fritz
Department of Study
Psychology
Discipline
Psychology
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
Ph.D.
Degree Level
Dissertation
Keyword(s)
Psychology, Psychometrics
Language
eng
Abstract
"Four studies were conducted to examine the psychometric properties of a new, resampling-based validity estimator which does not require a crossvalidation sample in order to produce unbiased estimates of validity. The first and second experiments were Monte Carlo simulations while the third and fourth applied the method to ""real"" data. In Experiment 1, a purely empirical method was found to be almost as effective as crossvalidation in debiasing the validity estimate; samples of 200 or more were found to be needed to produce valid empirical keys. In Experiment 2, a hybrid method which combines a priori model information was examined and found not to substantially improve the procedure unless the model information was of excellent quality (but the resampling estimator was also shown to be fairly robust to poor model information). Experiment 3 replicated the simulation results of Experiment 1 using ""real"" personality data and Experiment 4 compared the purely empirical keying to a hybrid method that blended empirical and a priori information for a biodata instrument. The results of these two experiments using empirical data confirmed many of the aspects of the simulations while pointing out some limitations of the simulated context. In general, the use of thresholds (minimum option-validities or number endorsing an option) to improve the robustness of the estimate was not strongly supported. The addition of a priori, model information in the hybrid keying only slightly improved upon the pure empirical approach. The hybrid keying method that relies most heavily on empirical information paired with a good model key allows samples as small as N = 100 to be keyed."
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
