[Rasch] Test Equating
ici_kalt at yahoo.com
Thu Dec 15 00:39:21 EST 2005
Concerning steps to be taken in advance, it could be
better if in advance you can produce two equally
difficult tests. Having an item bank of calibrated
items, you may organize similar tests balancing the
distribution of difficulties, including your anchor
items. Something like this is explained in Best Test
Design by Wright and Stone.
--- Rama Guinda <guinda36 at hotmail.com> wrote:
> Dear list members,
> I have a question regarding test equating. Id be
> appreciated if you
> I have two versions of a test which are supposed to
> measure one construct.
> One version is more difficult than the other one.
> Each test has 20 items
> with 5 items common to both versions.
> In order to be able to compare people who take
> different versions of the
> Is it enough to compute the logit scores for each
> person and directly
> compare them?
> I mean do the common items take care of everything?
> If not, then what other
> steps should be taken in advance to be able to
> compare the ability of people
> who take different versions of the test?
> A Camera Sells every 2 Minutes on eBay. Get Your's
> at a Great Price Now!
> Rasch mailing list
> Rasch at acer.edu.au
FAMILIA DE PROGRAMAS KALT.
Mariano Jiménez 1830 A
Col. Balcones del Valle
78280, San Luis Potosí, S.L.P. México
TEL (52) 44-4820 37 88, 44-4820 04 31
FAX (52) 44-4815 48 48
web page (in Spanish AND ENGLISH): http://www.ieesa-kalt.com
Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around
More information about the Rasch