[Rasch] Fwd: Question Concerning Rasch Analysis on Weighted Stage Data

Rense Lange rense.lange at gmail.com
Thu Jul 14 05:15:35 EST 2011


The way I understand your coding is that you "baked" items' difficulty right
into the numbers. What I would do is to take that out again first. This is
not really hard, if I understand things correctly, and if a common rating
scale was used.

For instance, if item 6 had difficulty 5 and the rating was 3, you had
coded: 3*5=15. So, just divide these rating products by their item's
difficulty index. Then run winsteps over rating scales / partial credit
items. Next, compare the whether items Rasch difficulty order is the same as
the one you had in mind when you started multiplying. You'd like them to
match ...


On Wed, Jul 13, 2011 at 1:30 PM, Michael Lamport Commons
<commons at tiac.net>wrote:

> Here's my question about the Rasch analysis.
> Question:
> We have been trying to measure participants' stages of development via
> surveys that participants to rate their preference for vignettes that
> differ in their order of hierarchical complexity on a 1 to 6 scale.. The
> vignettes are stories which show characters behaving at particular
> stages. My first assumption which I am not sure is an appropriate
> assumption, is that the items of greater difficulty -- higher order of
> hierarchical complexity) will rate. To analyze the data following Bond
> and Fox, we multiplied the response codes (Likert-scale-esque numbers
> 1-6) by item orders of hierarchical complexity to attain a weighted
> score. We then run a Rasch analysis on the weighted scores.
> Is Rasch analysis appropriate for this form of instrument. The "best"
> one can score on in rating a vignette instrument is 6 on the highest
> order question. But let us say the participant rates 6 on every item,
> even those lower in order of hierarchical complexity and therefore
> difficulty. According to our measurement system, the "best" one can
> score is 6 on every item. Rasch inherently assumes that all items
> measure the same thing, and that their measurement is INDEPENDENT of the
> other items, but this is clearly not the case. Am I wrong, and is Rasch
> appropriate here?
> My Best,
> Michael Lamport Commons, Ph.D.
> Assistant Clinical Professor
> Department of Psychiatry
> Beth Israel Deaconess Medical Center
> Harvard Medical School
> 234 Huron Avenue
> Cambridge, MA 02138-1328
> Telephone   (617) 497-5270
> Facsimile   (617) 491-5270
> Cellular    (617) 320–0896
> Commons at tiac.net
> http://dareassociation.org/
> _______________________________________________
> Rasch mailing list
> Rasch at acer.edu.au
> Unsubscribe:
> https://mailinglist.acer.edu.au/mailman/options/rasch/rense.lange%40gmail.com

Rense Lange, Ph.D.
via gmail
-------------- next part --------------
An HTML attachment was scrubbed...
URL: https://mailinglist.acer.edu.au/pipermail/rasch/attachments/20110713/a53a6a20/attachment.html 

More information about the Rasch mailing list