[Rasch] Equating problem

Stuart Luppescu s-luppescu at uchicago.edu
Wed Jun 28 07:26:30 EST 2006


Hi all, I have a tricky equating problem. I'm trying to equate two tests
using common people. However, one test was given under very high-stakes
conditions, and the other was given under NO stakes. Furthermore, the
no-stakes test was always given second. (The district authorities didn't
want anything interfering with or influencing results on the high-stakes
test.)

I did an equipercentile equating of the two tests, and found uniformly
lower performance on the no-stakes test. The results of the Rasch
equating showed similar performance by students on both tests. In two
grades on the math test, students did a bit better on the low-stakes
test (differences of .14 and .08 logits); in two grades on the reading
test, students did a bit better on the high-stakes test (differences
of .11 logits).

The question is, is there any way I can disentangle the effects of
differential effort due to differencens in stakes, from actual
differences in the tests? 

Thanks.
-- 
Stuart Luppescu -=-=- s-luppescu <AT> uchicago <DOT> edu
CCSR at U of C ,.;-*^*-;.,  www.consortium-chicago.org
     (^_^)/    才文と智奈美の父
Thank God I'm an atheist!
-------------- next part --------------
A non-text attachment was scrubbed...
Name: smime.p7s
Type: application/x-pkcs7-signature
Size: 3437 bytes
Desc: not available
Url : https://mailinglist.acer.edu.au/pipermail/rasch/attachments/20060627/8ee8bad5/attachment.bin 


More information about the Rasch mailing list