[Rasch] Why Rasch?

Robert Hess Robert.Hess at ASU.edu
Wed Nov 9 04:43:39 EST 2011


To Anthony and all others:

I respect each and every rationale presented, but I must take myself back
over 30 years ago, when I was first introduced to the Rasch model (blame Joe
Ryan for this). It was the simplicity of being able to understand that one
could place person ability (or achievement) on the same scale as item
difficulty. Furthermore, the notion that item discrimination was constant on
all items and that it was difficulty only that separated persons provided
that all persons in the analysis received equal exposure to the learning
experience. Once these events took place then the real beauty of the model
took place: one could now predict the probability of a person with a given
ability level successfully answering an item at a given difficulty level. It
also meant that items were truly indeed "person free" and I could build item
pools readily. It also meant that I must develop with greater care the items
that I used in my tests. Why? Because unlike the other models, I didn't
choose a model to fit my items, I had to choose items that fit my model.

In the early 1990s, the introduction of the many-faceted Rasch model only
increased my ability to further explore the factors influencing student
achievement.

Okay, I know for many I have been preaching to the choir.

 

Bob Hess

Prof. Emeritus of Measurement and Evaluation.

Arizona State University

  _____  

No virus found in this message.
Checked by AVG - www.avg.com
Version: 10.0.1411 / Virus Database: 2092/4004 - Release Date: 11/08/11

-------------- next part --------------
An HTML attachment was scrubbed...
URL: https://mailinglist.acer.edu.au/pipermail/rasch/attachments/20111108/2a98ef31/attachment.html 


More information about the Rasch mailing list