search

alexanderrobitzsch / TAM

Test Analysis Modules
https://alexanderrobitzsch.github.io/TAM/
15 stars 9 forks source link

irtmodel = "RSM" is not working when constraint = "items" #19

Closed xiaozhanzi closed 1 year ago

xiaozhanzi commented 1 year ago

Hi, Thank you for your package. It's a great package for doing the Rasch analysis which benefits me a lot. Recently, when I conducted the multidimensional Rasch analysis with the following syntax: TAM::tam.mml(resp = df, irtmodel = "RSM", constraint = "items", Q = Q2, control = list(maxiter = 200, snodes = 2000)) Instead of using the default setting, here I changed the constraint to "items". Everything went smoothly, but when I checked the result, it reported the PCM2 model results, not the "RSM" results. It's there something wrong with my syntax?

alexanderrobitzsch commented 1 year ago

I suppose that constraint="items" is not implemented for irtmodel="RSM". Maybe I do not see why one should ever employ the items constraint.

xiaozhanzi commented 1 year ago

Many thanks for your reply. I want to get a similar report like that in ConQuest. When doing the multidimensional Rasch analysis with "item+step" , ConQuest constrains the last item of each dimension and reports a general step statistic. I wonder if TAM can do a similar analysis with that in ConQuest? Appreciate your kind suggestion and help.

On Fri, Dec 9, 2022 at 1:43 AM Alexander Robitzsch @.***> wrote:

I suppose that constraint="items" is not implemented for irtmodel="RSM". Maybe I do not see why one should ever employ the items constraint.

— Reply to this email directly, view it on GitHub https://github.com/alexanderrobitzsch/TAM/issues/19#issuecomment-1343075540, or unsubscribe https://github.com/notifications/unsubscribe-auth/AZPTYFFAVLPPJIBKGXLQCOTWMIM4LANCNFSM6AAAAAASYDMBV4 . You are receiving this because you authored the thread.Message ID: @.***>