[Rasch] Rasch models for continuous data

Mike Linacre (RMT) rmt at rasch.org
Sun Mar 14 23:36:22 EST 2010


Thank you for your question, Anthony.

Rasch models for continuous ratings require the specification of a 
continuous threshold function, such as a polynomial. The choice of function 
is an arbitrary decision by the analyst. See www.rasch.org/rmt/rmt144a.htm

Experiments with continuous Rasch models indicate that it is more useful to 
chunk the continuous observations into finite intervals, and then model the 
intervals as categories using RSM or PCM. See www.rasch.org/rmt/rmt211b.htm

Does this help, Anthony?

Mike Linacre

At 3/14/2010, you wrote:
>Hans Muller has also a model called 'continuous ratings'.
>How is this different from RSM and PCM in assumptions as regards step 
>distances within and across items? And with which software can you do this 
>analysis?
>Anthony

Mike Linacre
Editor, Rasch Measurement Transactions
rmt at rasch.org www.rasch.org/rmt/ Latest RMT:  23:3 Winter 2009

-------------------------------------------------
Please consider the environment before you print
-------------- next part --------------
An HTML attachment was scrubbed...
URL: https://mailinglist.acer.edu.au/pipermail/rasch/attachments/20100314/8919b070/attachment.html 


More information about the Rasch mailing list