[Rasch] Negative pt-bis and fit of 1.0? How can this be?
trevor.bond at jcu.edu.au
Wed Mar 7 13:39:29 EST 2012
In the program RUMM for example, we interpret this number as evidence of the power of the test of fit, with a colour coding from Excellent, Good, Reasonable, Low, and Too Low.
This is a great idea, but look over the shoulder of some users. Some think the interpretation is:
this number as evidence (ooops, didn’t see this: of the power of the test) of fit, with a colour coding from Excellent, Good, Reasonable, Low, and Too Low.
Sometimes, it doesn’t matter how hard you try
Still a man hears what he wants to hear
And disregards the rest (Simon & Garfunkel)
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Rasch