# [Rasch] Why Rasch?

Stuart Luppescu slu at ccsr.uchicago.edu
Wed Nov 9 05:44:47 EST 2011

```On Tue, 2011-11-08 at 16:18 +0800, Anthony James wrote:
> Dear all,
> Reviewers of a journal have asked me to provide reasons why I have used Rasch model for validating a questionnaire and notother methods. Can you please tell me what should be written when one is asked such a question?
> Cheers
> Anthony
> _______________________________________________ Rasch mailing list Rasch at acer.edu.au Unsubscribe: https://mailinglist.acer.edu.au/mailman/options/rasch/slu%40ccsr.uchicago.edu

I can give you two good reasons:
1) We produce measures from annual surveys of students, teachers and
principals in the Chicago Public Schools. In reporting, we can use
expected responses on all the items to describe clearly what it means to
have a, say, 1.5 on a particular measure in terms of the responses that
person gave to all the items. We define ranges of performance (e.g.,
Very Weak, Weak, Strong, Very Strong) and can explicitly describe how
people in each of those ranges respond.
2) Each person measure comes with a standard error, which we inflate
depending on the amount of misfit (inflated.se = se * max(1,
sqrt(inmnsq)). The inverse of the inflated standard error can be used in
level 1 of a 3-level hierarchical model as a weight, with the level-1
variance fixed at 1.00. The level-2 outcome becomes the latent person
measure, or the person measure adjusted for measurement error. Level 3
is the school level. We feel this method gives us the best estimates of
school effects.

--
Stuart Luppescu -=- slu .at. ccsr.uchicago.edu
University of Chicago -=- CCSR

datayoda: Bing is my friend...I found the cumsum()
function. Dirk Eddelbuettel: If bing is your
friend, then rseek.org is bound to be your uncle.
-- datayoda and Dirk Eddelbuettel (after searching
for a function that       computes cumulative
sums)       stackoverflow.com (October 2010)

-------------- next part --------------
A non-text attachment was scrubbed...
Name: smime.p7s
Type: application/x-pkcs7-signature
Size: 3573 bytes
Desc: not available
Url : https://mailinglist.acer.edu.au/pipermail/rasch/attachments/20111108/422350e1/attachment.bin
```