[Rasch] Not a Fan of Lexiles?
Mike Linacre (RMT)
rmt at rasch.org
Fri Nov 2 17:01:08 EST 2007
Paul remarks: "look, all things Rasch is wonderful" -vs- my "is it really"
response is going nowhere.
Perhaps we are going nowhere so far, but critiques of Rasch can lead to
advances in Rasch theory or in communication of the theory.
Divgi's (1985) objection to Rasch, "coin-tossing fits the Rasch model"
actually identifies a virtue of Rasch. Rasch is ideal for analyzing
computer-adaptive-testing data where the item difficulties are deliberately
targeted on the person abilities - so that responses look like coin-tosses.
Our communication of Rasch theory had been deficient.
Or McDonald's (1986) identification of a flaw in Rasch fit statistics,
"they are insensitive to some forms of multidimensionality" became the
basis of an exploratory technique in Rasch analysis. Our implementation of
Rasch theory had been deficient.
Or Dickson & Kohler's (1996) list of objections to Rasch ("Rasch assumes,
is inexact, is imprecise," etc.) forced us into a systematic response which
helped confirm the model as a latter-day version of Pythagoras' Theorem.
Our philosophical basis of Rasch theory had been deficient.
Let's hope that new critiques, new deficiencies, and so new opportunities
and new excitement, keep on coming to light ....
Editor, Rasch Measurement Transactions
rmt at rasch.org www.rasch.org/rmt/ Latest RMT: 21:1 Summer 2007
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Rasch