This web site provides the software program DIFdetect for use with STATA v. 7.0 or v. 8.0.

The present version of DIFdetect is version 1.2. Please send us feedback so we can improve future versions.

DIFdetect analyzes test data for the presence of items with differential item functioning (DIF) using ordinal logistic regression techniques first suggested by Zumbo (Zumbo, B.D. A Handbook on the Theory and Methods of Differential Item Functioning (DIF): Logistic Regression Modeling as a Unitary Framework for Binary and Likert-type (Ordinal) Item Scores. Ottawa ON: Directorate of Human Resources Research and Evaluation, Department of National Defense, 1999).

DIFdetect uses different criteria than those suggested by Zumbo to determine whether DIF is present in each item. For more details please refer to our documentation.

DIFdetect has been used in a number of studies. A growing list will be kept here. Please email us with updates so we can keep this list current.

DIFdetect was written by
Paul K. Crane, MD
Lance Jolley, BS
and
Gerald van Belle, PhD

Dr. Crane was supported as an NRSA General Internal Medicine Fellow at the University of Washington
Mr. Jolley and Dr. van Belle were supported by NIH grant AG16976.

Copyright © University of Washington, 2003.

From this site you can view our documentation.
After agreeing to the licensing agreement, you can download the .do and .hlp files.

Please send us questions, comments, and feedback at difdet@u.washington.edu.