Publication Date
Spring 2020
Advisor(s) - Committee Chair
Reagan D. Brown (Director), Katrina A. Burch, and Elizabeth L. Shoenfelt
Degree Program
Department of Psychological Sciences
Degree Type
Master of Science
Abstract
The objective of this study is to empirically test existing techniques to calculate the likely range of values for a Classical Test Theory true score given an observed score. The traditional method for forming these confidence intervals has used the standard error of measurement (SEM) as the basis for this confidence interval. An alternate equation, the standard error of estimate (SEE), has been recommended in place of the SEM for this purpose, yet it remains overlooked in the field of psychometrics. It is important that the correct equation be used in various applications in personnel psychology. Monte Carlo analyses were conducted to investigate the performance of the various methods for computing a confidence interval around an observed score. Results indicated that the SEE equation used with an observed score regressed to the mean most accurately and efficiently located an individual’s true score.
Disciplines
Human Resources Management | Industrial and Organizational Psychology | Statistical Methodology | Statistical Models | Statistical Theory
Recommended Citation
Wichert, Elayna, "A Monte Carlo Analysis of Standard Error-Based Methods for Computing Confidence Intervals" (2020). Masters Theses & Specialist Projects. Paper 3203.
https://digitalcommons.wku.edu/theses/3203
Included in
Human Resources Management Commons, Industrial and Organizational Psychology Commons, Statistical Methodology Commons, Statistical Models Commons, Statistical Theory Commons