This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.

Abstract Details

Activity Number: 360
Type: Contributed
Date/Time: Tuesday, August 3, 2010 : 10:30 AM to 12:20 PM
Sponsor: Biometrics Section
Abstract - #308623
Title: Integrated Test Information
Author(s): S. McKay Curtis*+ and Paul K. Crane
Companies: University of Washington and University of Washington
Address: Department of Statistics, Seattle, WA, 98195,
Keywords: bifactor model ; psychometrics ; nuisance parameters

In the study of cognitive diseases, a goal of many data analyses is to estimate a general cognitive ability of individuals. Tests designed to measure this ability are evaluated using test information (TI)---a measure of how precisely the test can estimate abilities. Formulas for TI in basic item response theory (IRT) models are well known. However, these models often provide poor fit to real data, and multidimensional IRT or item factor analysis models may be used to account for residual correlation or nuisance factors. In these advanced models, it may still be important to have a measure of TI for the general ability factor. We derive a measure of TI that accounts for nuisance factors and residual correlation by integrating over the nuisance factors in the likelihood. We demonstrate this method using a data set from Alzheimer's Disease Neuroimaging Initiative.

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 2010 program

2010 JSM Online Program Home

For information, contact or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.