[Rasch] Rasch and Missing data
ici_kalt at yahoo.com
Sat Jul 5 02:42:19 EST 2008
In addition it is clear that we can take this up to the limit. A "clever" student may analyze the full set of items, and so he decides to answer only one where he is completely certain to have the correct answer and he gets 1/1: a perfect score indeed!.
I must say that we had this type of "clever" patterns in teacher's evaluation (teachers are more difficult to evaluate and measure than students), so we decided not to consider the blank answers as missing but as wrong. You can do this with Winsteps for instance. Some people considers this as a penalty for missing responses, and so illegal, be careful.
FAMILIA DE PROGRAMAS KALT.
Ave. Cordillera Occidental No. 635
Colonia Lomas 4ª San Luis Potosí, San Luis Potosí.
C.P. 78216 MEXICO
(52) (444) 8 25 50 76
(52) (444) 8 25 50 77
(52) (444) 8 25 50 78
web page (in Spanish AND ENGLISH): http://www.ieesa-kalt.com
--- On Fri, 7/4/08, Anthony James <luckyantonio2003 at yahoo.com> wrote:
From: Anthony James <luckyantonio2003 at yahoo.com>
Subject: [Rasch] Rasch and Missing data
To: rasch at acer.edu.au
Date: Friday, July 4, 2008, 11:25 AM
It is generally argued that RM is robust to missing data because the total score is the sufficient statistic for parameter estimation.
But, missing data affects total score too. Suppose that in a complete data set the total score of a person is 25 out of 30. If this dataset is affected by ‘missingness’ then the total score of this person would be say, 21 out of 30. If his measure when there’s no missing data is say, 2 logits (based on 25/30) his measure from the ‘missingness struck’ dataset would be say, 1.5 logits because some of his correct answers are missing and his raw score diminishes (21/30). So the measure we get is not equivalent to what we would have got when all data were present.
Rasch mailing list
Rasch at acer.edu.au
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Rasch