[Rasch] Difficulty Performing Rasch Analysis in R.

Rense Lange rense.lange at gmail.com
Tue May 3 11:15:44 AEST 2016


You have to make at least two item 'groups' (in Winsteps terms), the binary and the ternary. Groups are bunches of items with a common rating scale structure. If the R programs cannot do this (I dont know this) you could download the free Bigsteps software...

Rense Lange

Sent from my iPhone

On May 2, 2016, at 18:16, Nicholas Commons-Miller <ncommons at gmail.com> wrote:

Dear Rasch listserv,

I am trying to analyze my data, which has 67 binary items and 5 ternary items. I am trying to analyze it using a package called eRm (version 0.15-6) in R statistics. I am successful able to analyze the first 67 items using basic Rasch analysis, but I am failing to analyze the entire set of items at once. I have tried to do it with RSM, PCM, and LRSM (all included in the eRm package), but have not been successful with any of them. Conceptually, I think that LRSM should be the correct one.

I have attached the data in TXT format. It consists of 72 columns (the items) and 80 rows (the participants).

Any insight on which analysis to use and how to use it would be greatly appreciated.

My best,
Nicholas Commons-Miller
<DATAOUT.txt>
________________________________________
Rasch mailing list
email: Rasch at acer.edu.au
web: https://mailinglist.acer.edu.au/mailman/options/rasch/rense.lange%40gmail.com


More information about the Rasch mailing list