[Rasch] Deciding Items are Identical
rense.lange at gmail.com
Sat Dec 11 09:40:21 EST 2010
Well, your items almost certainly will NOT be of equal difficulty - and
Facets has a statistical test that will tell you if this is so. But, they
might be "close enough" for some purposes perhaps - although I'm doubtful
about that too.
Of course, you might constrain all items to be of the same difficulty (say,
0), and see what happens to the item / model fit and item displacement.
Just to be sure: if you are making this unrealistic equality assumption
because you believe that this is needed for "equivalent" forms or test
results or something like that, then don't do this. There are much better
ways to deal with such situations ...
On Fri, Dec 10, 2010 at 3:44 PM, Tom Conner <connert at msu.edu> wrote:
> Consider that you have a set of items, in my case vignettes, that are
> superficially different but you would like them to all have the same
> item difficulty within error. How do you test for that? The responses
> to the vignettes are polytomous.
> Tom Conner
> Professor of Sociology
> Michigan State University
> office: 517 355-1747
> cell: 517 230-0343
> "What if there were no hypothetical questions?"
> Rasch mailing list
> Rasch at acer.edu.au
Rense Lange, Ph.D.
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Rasch