search

hyunsooseol / snowRMM

Latent Class Analysis(LCA), LCA for ordinal indicators, Latent class growth modeling, Laten Profile Analysis, Rasch model, Linear Logistic Test Model, Rasch mixture model, linear and equipercentile equating can be performed within module.
7 stars 2 forks source link

RMM issues #10

Closed hoonjinn closed 7 months ago

hoonjinn commented 2 years ago

Dear Dr. Seol,

I hope you are doing well and I always appreciate your amazing works in Jamovi ecology.

I have a quick question about the Rasch Mixture model.

Even though I use the same dataset and enter the same conditions (e.g., class number: 3, step:1 - dichotomous data type), the information criteria values are substantially changed (i.e., sometimes, the final model is changed) whenever I try to execute the model. I might be wrong, but could you explain why it happens?

Thank you,

Best, Hoonjin

hyunsooseol commented 2 years ago

Hi Hoonjin

Thanks for your question. the issues that you asked me is involved in , for example, set seed in R. If we randomly select some observations for any task in any statistical software it results in different values all the time and this happens because of randomization. The use of set. seed is to make sure that we get the same results for randomization.

But, I did not use set seed option in jamovi. this is not the problem in the result of Rasch mixture model. Just report one of the results that you try, say class 3, step 1.

Cheers Seol

hoonjinn commented 2 years ago

Hello Dr. Seol,

Thanks for your prompt response! It was really helpful and I try to set a seed number to get consistent IC values! :)

Best, Hoonjin

hoonjinn commented 2 years ago

Hello Dr. Seol,

I have another question while using your RMM modules (it was so comfortable, but helpful tools for researchers).

I was wondering whether item parameters and fit statistics in RMM are equivalent to those estimated separately from each latent class. Plus, I would like to cite your package in my ongoing manuscripts, and I would be grateful if you let me know the citation for your modules.

Looking forward to hearing from you.

Thank you,

Best, Hoonjin

hyunsooseol commented 2 years ago

Hi Hoonjin

Could you send me an .omv file as a zip that arise issue. I will take a look at.

For the citation of my module, for example, the analysis was performed by using snowRMM(Seol, 2022) module in jamovi.

Seol, H. (2022). snowRMM: Rasch Mixture Model for jamovi. [jamovi module]. Retrieved from https://github.com/hyunsooseol/snowRMM.

Cheers Seol