[Rasch] Scaling ranks
Mike Linacre (RMT)
rmt at rasch.org
Mon Nov 10 10:25:25 EST 2008
Thank you for your question, Don.
Rasch-analyzing your rankings as ratings on a partial-credit rating-scale
works well. JAM 7:1 p. 129-136. This also allows for tied rankings and
missing data. See also www.rasch.org/rmt/rmt82p.htm .
An example in which golf tournaments are used to rank players is shown at
At 11/9/2008, you wrote:
> I have a survey wherein respondents rank the importance of 20 items (a
> difficulty task, I know). I'd like to aggregate the responses and scale
> the results. I could translate the ranks into paired comparisons and
> then apply Thurstone, but it seems like there would be a much easier way
> with Rasch. Can someone point me in the right direction?
Editor, Rasch Measurement Transactions
rmt at rasch.org www.rasch.org/rmt/ Latest RMT: 22:1 Summer 2008
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Rasch