skip to main content skip to footer

Using the Kernel Method of Test Equating for Estimating the Standard Errors of Population Invariance Measures RMSD

Author(s):
Moses, Tim P.
Publication Year:
2006
Report Number:
RR-06-20
Source:
ETS Research Report
Document Type:
Report
Page Count:
25
Subject/Key Words:
Population Invariance, Test Equating, Standard Error of Equating, Kernal Method

Abstract

Derivations based on the kernel method’s standard error formulas are given for computing the standard errors of the root mean square difference (RMSD) and of the simple difference between two subpopulations’ equated scores. An investigation of popular invariance for the equivalent groups design is discussed. The accuracy of the derived standard errors is evaluated with respect to empirical standard errors. This evaluation shows that the accuracy of the standard error estimates for the equated score differences is better than for the RMSD, and that accuracy for both standard error estimates is best when sample sizes are large.

Read More