Abstract #301784

This is the preliminary program for the 2003 Joint Statistical Meetings in San Francisco, California. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 2-5, 2003); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2003 Program page
JSM 2003 Abstract #301784
Activity Number: 449
Type: Contributed
Date/Time: Thursday, August 7, 2003 : 8:30 AM to 10:20 AM
Sponsor: Social Statistics Section
Abstract - #301784
Title: A Comparison of Rasch Item and Person Parameter Estimation Recovery Under Missing Data Conditions Within Item Response Theory and Hierarchical Linear Modeling Frameworks
Author(s): Tiffany A. Whittaker*+ and Rachel T. Fouladi and Carolyn F. Furlow
Companies: University of Texas and University of Texas M.D. Anderson Cancer Center and Student
Address: 1240 Barton Hills Dr. #123, Austin, TX, 78704,
Keywords: Item Response Theory ; Rasch model ; hierarchical linear modeling ; missing data
Abstract:

The equivalence between the Rasch model and the hierarchical generalized linear model (HGLM) was demonstrated by Kamata (1999, 2001), resulting in the one-parameter hierarchical generalized logit model (1-P HGLLM). This allows simultaneous estimation of item and person parameters within a Hierarchical Linear Modeling (HLM) framework compared to the two-step process of estimation within traditional Item Response Theory (IRT). A problem in educational testing is the adverse impact that missing item responses can have on the estimation process. When using traditional IRT estimation software, such as PARSCALE (Muraki & Bock, 1993), missing item responses are deleted listwise. Under the HLM framework, other software may be used, such as PROC MIXED, which has the ability to impute missing item responses using a maximum likelihood procedure. The purpose of this study is to evaluate the recovery of Rasch item/person parameters under realistic missing data conditions using traditional IRT estimation with PARSCALE and HLM estimation with PROC MIXED. Additional conditions will be varied (viz., sample size, number of items, ability distributions, and missing data patterns).

  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2003 program

JSM 2003 For information, contact meetings@amstat.org or phone (703) 684-1221. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2003