[Rasch] DIF test with 2-item scale

Thomas Salzberger thomas.salzberger at gmail.com
Wed Jan 4 02:40:57 AEDT 2017


Technically speaking, I  guess, it is possible to run a dif test. If the
difference between the two items is not the same, there would be dif.
However, you would not be able to distinguish between the first item
showing dif, the second (the other item would exhibit artificial dif) , or
both. Unless you *know* that one item is free of dif.

As dif is, in a sense, always relative, the more items with no dif the
better. Even with 3 or 4 items it may not always be easy to find out which
item(s) really show dif.


Dr. Thomas Salzberger
WU Wien University of Economics and Business (Austria)
Modus Outcomes - Psychometric Consulting Associate
MBC Matilda Bay Club
Thomas.Salzberger at gmail.com
Thomas.Salzberger at wu.ac.at

Am 02.01.2017 20:06 schrieb "Randy and Shelley MacIntosh" <
srmac at fastmail.com>:

I have several two-item scales. I am guessing that it is impossible to test
for DIF.
Is that correct?
Any suggested reading on the minimum number of items required to test for
DIF in a Rasch model would be appreciated.

Randy MacIntosh

Rasch mailing list
email: Rasch at acer.edu.au
web: https://mailinglist.acer.edu.au/mailman/options/rasch/thomas
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailinglist.acer.edu.au/pipermail/rasch/attachments/20170103/68a99ae8/attachment.html>

More information about the Rasch mailing list