Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: equating scores


From   Stas Kolenikov <[email protected]>
To   [email protected]
Subject   Re: st: equating scores
Date   Fri, 13 May 2011 09:19:14 -0500

On Thu, May 12, 2011 at 10:59 PM, Hee Jin Bang <[email protected]> wrote:
> I have 3 sets of scores of student writing samples. These scores are of the SAME papers scored by different scorers in three consecutive years.
>
> The syntax I have been working with is--  linequate anchortest newtest oldtest , which calculates constants needed to equate the new test to an old test, using an anchor test. This assumes that there are different items in the two tests, and that there is an anchor test which was administered to both old test takers and new test takers.  This is not a correct assumption for the situation I have on hand, where the same test that was taken by the same group of students are scored by different raters in different time points.
>
> Does anyone know of the appropriate syntax I should use? I'd be very grateful
> for your help.

There aren't very many measurement people on the list, so you are very
likely on your own here. If I were doing this, I would run my -confa-
on it (http://www.citeulike.org/user/ctacmo/article/9101176), which
would give me an idea about measurement invariance, get the predicted
factor scores (which in this case boils down to the linear combination
of the tests with weights inversely related to unique variances) and
transform them so that they have the desired range or mean/standard
deviation combination.

-- 
Stas Kolenikov, also found at http://stas.kolenikov.name
Small print: I use this email account for mailing lists only.

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index