[Rasch] Partial credit and rating scale

Anthony James luckyantonio2003 at yahoo.com
Sun May 21 18:53:10 EST 2006

Dear list members,
  I think it’s the right time I bring up a problem of mine regarding the rating scale and partial credit model.
  I have four polytomous super-items each with 25 locally dependent items.
  I Rasch analysed them with winsteps.
  When I use the rating scale model, which I think is the default in Winsteps, it’s ok.
  But when I use partial credit model (Groups=0) the order of difficulty of items change and this order of difficulty does not match with the raw score of the items. An item with raw a score of  2151 has a higher measure than an item with a raw score of 1867!! How come?
  Which model should I use here?
  Thanks a lot

Be a chatter box. Enjoy free PC-to-PC calls  with Yahoo! Messenger with Voice.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: https://mailinglist.acer.edu.au/pipermail/rasch/attachments/20060521/97fb8c05/attachment.html 

More information about the Rasch mailing list