[Rasch] Test equating using TCCs and Item anchor files

Imogene Rothnie irothnie at usyd.edu.au
Wed Aug 3 13:45:43 EST 2011


I have 2 versions of a test with 8 common items Test A original and Test
B secondary. (2 different cohorts of students) 

When I anchor Test B with the common items from Test A and run a
Winsteps analysis the Mean measure of the items is -0.32 logits, an
easier test in the frame of reference of Test A if I am interpreting
this output correctly.

However, when I use MFORMS and compare the test characteristic Curves of
the two tests, the expected score for Test A at ability 0 logits is 32.7
whereas the expected score for Test B at 0 Logits ability is 27.26.

Am I correct in interpreting these results as suggesting that although
test C was a little easier than Test B, the student ability for Test C
was lower than Test B? 

Basic question I realise but we are just beginning to use Rasch tools to
equate tests properly .

Many thanks


IMOGENE ROTHNIE | Lecturer (Assessment) 
Office of Medical Education | Faculty of Medicine             

Rm 108, Edward Ford Bdg  A27 | The University of Sydney | NSW | 2006

T +61 2 9036 6434  | F +61 2 9036 7580   | M +61 418 381 359  
E imogene.rothnie at sydney.edu.au <mailto:imogene.rothnie at sydney.edu.au>
| W http://ome.med.usyd.edu.au <http://sydney.edu.au>  

This email plus any attachments to it are confidential. Any unauthorised
use is strictly prohibited. If you receive this email in error, please
delete it and any attachments.

Please think of our environment and only print this e-mail if necessary.


-------------- next part --------------
An HTML attachment was scrubbed...
URL: https://mailinglist.acer.edu.au/pipermail/rasch/attachments/20110803/972886f8/attachment.html 

More information about the Rasch mailing list