# [Rasch] item bank

Agustin Tristan ici_kalt at yahoo.com
Fri Oct 13 08:08:12 EST 2006

```Hi Svend: Theoretically and Practically you're correct. BUT only if you're measuring people. I believe that once the people will answer a pool of items previously known from the bank, they are not in a measuring situation.

Let's imagine a extreme theoretical case:
A student of physics and a professor know in advance the 30 items (or 300 or 1000) from the bank, your test will only include items from that bank. Let's imagine they study the item bank and know the responses of those items, under such circumstances, they will get the same raw score, as they will solve the same amount of items, hence they will get the same measure. In fact they don't know the same things, they must have a different measure if you provide a test to measure their knowledge and abilities. But now you are not measuring them, you are counting the items they previously have learned from the bank. Even if the 30 items come from a sample of the complete domain we're going to test, once you know these 30 items, the domain is  reduced to a finite domain of 30/30.

I cannot do the same consideration in a real test. I believe the test condition is different.

Hope it helps.
Agustin

Svend Kreiner <S.Kreiner at biostat.ku.dk> wrote:
I am not sure I understand this. I thought that the whole idea about specific objectivity in Rasch models was the (relative) difficulties of items does not depend on the sample of persons and on whether or not other items are included in the test.

The item parameters only provide measures of relative difficulties, e.g. the difference between the difficulty of item A and item B. This difference is the same whether or not you have observed a response to item C. So in which sense is the difficulty of items A and B reduced by inclusion of C in the item bank?

Best regards

Svend Kreiner

Agustin Tristan skrev:     Another thing Iasonas:
Once you have an "open" item bank, is it useful to calibrate the items? the difficulty of the items will ve reduced, even most of them will be solved by mostly all people...so the initial calibration has nothing to do with the original calibration.
This is another important topic to discuss.
Regards
Agustin Tristan

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

---------------------------------
Stay in the know. Pulse on the new Yahoo.com. Check it out.

---------------------------------
_______________________________________________  Rasch mailing list  Rasch at acer.edu.au  http://mailinglist.acer.edu.au/mailman/listinfo/rasch

--   Svend Kreiner  Associate professor  Department of Biostatistics    University of Copenhagen     Øster farimagsgade 5, entr. B  P.O. Box 2099  DK-1014 Copenhagen K, Denmark    Email: S.Kreiner at biostat.ku.dk  Phone: (+45) 35 32 75 97         Fax: (+45) 35 32 79 07

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!?
Get on board. You're invited to try the new Yahoo! Mail.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: https://mailinglist.acer.edu.au/pipermail/rasch/attachments/20061012/fcdcf1cc/attachment.html
```