[Rasch] rating scale and/or partial credit? or my wrong hunch?
trevor.bond at jcu.edu.au
Sat Oct 3 19:03:45 AEST 2015
It is always better to use original data, rather than any conflation of them.
Sent from 007's iPad
On 3 Oct 2015, at 5:58 AM, Shirin Shirazi <shirin.shirazi at gmail.com<mailto:shirin.shirazi at gmail.com>> wrote:
Dear List Members,
First, after a week of hard work, I would say "great job". Have a memorable weekend.
Then, I doubt that is there any possibility to Rasch-analyze essays considering both rating scale and partial credit? See, I have not recently looked at Test of written English (TOEFL iBT) scoring which is reported 0-30 in range but actually it has also some qualitatively-based rubrics: 1-16 limited 17-23 fair and 24-30 good. When it comes to Facets, is it alright to take it as a major facet, say ratings, then naming them R30, limited A, fair, B, and good, C or is it OK to write just the model, R30; observations are ratings in range 0-30 without further elaboration?
Something that is baffling is they are not items with the total of 30; besides, they are scales since they are ranging between 0-5 then scaled into 0-30; then they are divided into three different bands: limited, fair, good?
Your comments are highly welcome.In advance, I appreciate your invaluable comments as always have been .
Rasch mailing list
email: Rasch at acer.edu.au<mailto:Rasch at acer.edu.au>
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Rasch