A New IRT Approach to Test Construction and Scoring Designed to Reduce the Effects of Faking in Personality Assessment: The Generalized Graded Unfolding Model for Multi -Unidimensional Paired Comparison Responses
Stark, Stephen Edward
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/2142/82023
Description
Title
A New IRT Approach to Test Construction and Scoring Designed to Reduce the Effects of Faking in Personality Assessment: The Generalized Graded Unfolding Model for Multi -Unidimensional Paired Comparison Responses
Author(s)
Stark, Stephen Edward
Issue Date
2002
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, Personality
Language
eng
Abstract
Responses to personality items can be influenced by motivational factors present in the testing situation. In employment settings, individuals may fake good to raise their scores and increase their chances of being hired; in judicial settings, individuals may fake bad to lower their scores and reduce the likelihood of being judged mentally competent. Historically, researchers have tried to reduce the untoward effects of faking by using post hoc score adjustments, based on social desirability scores, but these approaches have had little salutary effect on validity and utility. Consequently, this research focuses on developing personality items and tests that are fake-resistant. Paired comparison responses to personality items, consisting of pairs of statements on different dimensions, which are similar in social desirability, are scored using a new multi-unidimensional item response theory model, called the GGUM-MU. Equations for the GGUM-MU item response and information functions are derived, a statistical method for examining model-data fit is illustrated, and the results of simulation studies to investigate the accuracy of a Bayes modal latent trait estimation procedure for one- and two-dimensional tests of various lengths are presented. The potential application of the GGUM-MU approach to personality test construction in organizational settings is also addressed.
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.
