[Rasch] Using Rasch Model to reduce Test Questionnaire

Roger Graves rgraves at uvic.ca
Wed Jun 27 02:46:07 EST 2012


Dear Juanito,

Two works of my students that illustrate the use of Rasch analysis to  
reduce the number of items are:

Graves, R. E., Bezeau, S. C., Fogarty, J., & Blair, R. (2004). Boston  
Naming Test Short Forms: A Comparison of Previous Forms with New Item  
Response Theory Based Forms. Journal of Clinical and Experimental  
Neuropsychology, 26, 891-902.
This is available online at:
http://web.uvic.ca/psyc/graves/Papers/JCEN-BNT_2004.pdf
This study used Rasch analysis to reduce the number of items to  
create short form versions (original 60 item test reduced to 30 and  
15 item versions).

Chia, A.-L. (2008). An investigation of cultural influence upon  
depressive symptomatology and its comorbid anxiety symptoms among  
Chinese Canadian university students. Unpublished doctoral  
dissertation, University of Victoria.
This is available online at:
https://dspace.library.uvic.ca:8443//handle/1828/2559
See pages 95ff for the Rasch analysis. This study did not  
specifically aim at reducing the number of items, but rather at  
retaining as many as possible that fit the model, then using  
differential item function analyses to retain only items that passed  
the DIF criteria for the two cultural groups.

There are many approaches to using analysis results to select items  
for deletion, and some may disagree with the approaches used in the  
above papers, but these papers will provide examples.

I have "cookbook" guideline handouts that I prepared for a graduate  
Psychometrics course where the student project was to design a new  
questionnaire and then to use Rasch and other analyses to select  
items for retention. Please contact me directly if you are interested  
in this.

With best wishes,

Roger

Roger Graves, Ph.D., Assoc. Prof. (Emeritus)
University of Victoria
Victoria, BC
Canada


On 23-Jun-12, at 2:37 AM, Juanito Talili wrote:

> Dear all,
>
> I would ask everyone to please post the papers that used Rasch  
> Model in reducing the number of items of a test questionnaire.
>
> Thank you.
> J
> _______________________________________________
> Rasch mailing list
> Rasch at acer.edu.au
> Unsubscribe: https://mailinglist.acer.edu.au/mailman/options/rasch/ 
> rgraves%40uvic.ca








More information about the Rasch mailing list