[Rasch] Fw: Re: Validity in Rasch

Juanito Talili talilij at yahoo.com
Tue Mar 22 02:26:13 EST 2011


Dear Dr Linacre,
 
I got the following guidelines from your paper (http://www.winsteps.com/a/linacre-optimizing-category.pdf) .  Thank you for that paper.  At the right of each guideline (in italics font) are my comments/questions.
 
1. At least 10 observations of each category. - It can be tested by inspection from the frequency distribution.
2. Regular observation distribution. - It can be tested by inspection from the frequency distribution.
3. Average measures advance monotonically with category. Where can I find this from the Winsteps outputs?
4. OUTFIT mean-squares less than 2.0. - I can easily locate this.
5. Step calibrations advance - I cant identify/locate this from the Winsteps outputs.  Please guide me.
7. Step difficulties advance by at least 1.4 logits. - I cant identify/locate this from the Winsteps outputs.  Please guide me.
 
A million thanks in advance.
J



--- On Mon, 3/21/11, Juanito Talili <talilij at yahoo.com> wrote:


From: Juanito Talili <talilij at yahoo.com>
Subject: Re: [Rasch] Validity in Rasch
To: "Mike Linacre" <rmt at rasch.org>
Date: Monday, 21 March, 2011, 3:21 PM







Dear Dr Linacre,
 
I got the following guidelines from your paper (http://www.winsteps.com/a/linacre-optimizing-category.pdf) .  Thank you for that paper.  At the right of each guideline (in italics font) are my comments/questions.
 
1. At least 10 observations of each category. - It can be tested by inspection from the frequency distribution.
2. Regular observation distribution. - It can be tested by inspection from the frequency distribution.
3. Average measures advance monotonically with category. Where can I find this from the Winsteps outputs?
4. OUTFIT mean-squares less than 2.0. - I can easily locate this.
5. Step calibrations advance - I cant identify/locate this from the Winsteps outputs.  Please guide me.
7. Step difficulties advance by at least 1.4 logits. - I cant identify/locate this from the Winsteps outputs.  Please guide me.
 
A million thanks in advance.
J

--- On Mon, 3/21/11, Mike Linacre <rmt at rasch.org> wrote:


From: Mike Linacre <rmt at rasch.org>
Subject: Re: [Rasch] Validity in Rasch
To: "Juanito Talili" <talilij at yahoo.com>
Date: Monday, 21 March, 2011, 2:54 PM


Thank you for your email, Juanito.

Winsteps misfit diagnosis is aimed at the practical problem of identifying and solving misfit problems, rather than the typical statistical misfit investigation based on hypothesis testing. 

Please look at http://www.winsteps.com/winman/index.htm?diagnosingmisfit.htm (in Winsteps Help). 

OK?

Mike L.

At 3/21/2011, you wrote:

Dear Dr Linacre,
Since Winsteps is available in my organization I would stick to learn first on "parameter-level tests of the assumptions" as you have mentioned.  Can you please give me some references/reading materials that deal on these parameter-level tests of the assumptions. 
 
Mike Linacre
Editor, Rasch Measurement Transactions
rmt at rasch.org www.rasch.org/rmt/ Latest RMT:  24:4 Spring 2011 


-------------- next part --------------
An HTML attachment was scrubbed...
URL: https://mailinglist.acer.edu.au/pipermail/rasch/attachments/20110321/8b6cbacb/attachment.html 


More information about the Rasch mailing list