[Rasch] sufficient statistic

Mike Linacre rmt at rasch.org
Mon Jul 16 09:12:58 EST 2012


Elizabeth:

We can derive the Rasch model from the axiom that the raw scores are the 
sufficient statistics for person ability and item difficulty.

http://www.rasch.org/rmt/rmt32e.htm

This also demonstrates that most of Classical Test Theory, which acts as 
though the raw scores are sufficient statistics for decision-making, is 
based on the implicit assumption that the Rasch model holds for their data !!

Mike L.

Mike Linacre
rmt at rasch.org www.rasch.org/rmt/ Latest RMT 26:1 Summer 2012
-------------- next part --------------
An HTML attachment was scrubbed...
URL: https://mailinglist.acer.edu.au/pipermail/rasch/attachments/20120716/c84fdf97/attachment.html 


More information about the Rasch mailing list