Show Posts

This section allows you to view all posts made by this member. Note that you can only see posts made in areas you currently have access to.

Topics - JerredJolin

Pages: [1]

I'm attempting to fit a partial credit model to a set of data (Conquest 4). 73 students rated 37 statements with a 6-point likert scale. Due to category sparseness in the response vector, I collapsed the 6 categories into three.

When I attempt to fit the model, I get the error code in the subject line. Attached here is a screenshot showing this. Also, I've attached the command, data, and labels files.

Could this have to do with the fact that by collapsing the categories many of the response sequences are perfect scores (e.g., now, something like 45% of the response sequences are all 2s).

Thanks for your continued assistance,



I'm receiving the following error message using Conquest 4:

Record missing in data file or data record is too long

A bit about the data:

221 teachers rated 37 statements using a 5-point likert scale. Additionally, they provided responses to 5 demographic questions (see attached labels file).

I created one fake case (id #221 in the attached data file) because I did not have an observation in category 0 of item 25. This fake case has missing data on all demographic questions and all rating scale items, except #25 for which the score is in category 0.

I've double-checked to ensure that the format statement in the attached Command file corresponds with the order of the data in each row and confirmed that there are observations for each of the categories of the 5 demographic questions in the data.

Looking through the Conquest Command Reference manual has not been very helpful.

Appreciate any support I might get on resolving this issue.


Pages: [1]