JSM 2012 Home

JSM 2012 Online Program

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

Online Program Home

Abstract Details

Activity Number: 424
Type: Contributed
Date/Time: Tuesday, July 31, 2012 : 2:00 PM to 3:50 PM
Sponsor: Statistics in Mental Health Research
Abstract - #305936
Title: Psychometric Method of Item Selection from an Item Bank to Create a Screening Test
Author(s): Douglas Tommet*+ and Frances M Yang and Paul K Crane and Sharon K Inouye and Edward R Marcantonio and Richard N Jones
Companies: Institute for Aging Research/Hebrew Senior Life and Institute for Aging Research/Hebrew Senior Life and University of Washington and Institute for Aging Research/Hebrew Senior Life and Harvard Medical School/Beth Israel Deaconess Medical Center and Institute for Aging Research/Hebrew Senior Life
Address: 1200 Centre Street, Boston, MA, 02131, United States
Keywords: Variable selection ; Item Response Theory

Typically, in creating short screening test from a longer, established test, standard variable selection procedures such as stepwise regression are used to determine which items to include in the screening test. These approaches ignore the psychometric properties of the items. We propose using Item Response Theory to inform the item selection. Specifically, we propose selecting items on the basis of the item's Information at a specified percentile of the latent trait of the subpopulation that is 'true positive'. This work is motivated from a study on the creation of a brief delirium screening instrument. The item bank was composed of orientation items from the Mini-Mental State Examination, the Digit Span test, and the Delirium Symptom Interview. Data from that study is used in a simulation analysis to compare this method to several other variable selection methods.

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 2012 program

2012 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

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