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

Missing data #22

Closed Wilcoxmp closed 4 months ago

Wilcoxmp commented 4 months ago

I have not been able to run even basic models with missing data. I have tried to code in different ways. Is there something I'm missing to be able to run data with missing data?

Matthew

hyunsooseol commented 4 months ago

Hi Matthew

What kind of analysis are you trying to run in snowRMM module? Could you share .omv file that cause errors? Zip it up and attach it in the board.

Kind Regards Seol

Wilcoxmp commented 4 months ago

Eng_Adpt_Binary.csv

I have included both the .csv and the zipped .omv file. The data comes from an adaptive test I was asked to evaluate, with a total 291 students across a possible 55 items. It may be that the data is too sparse with all items. I have been able to run subsections of the data successfully, but the whole data set doesn't work. I have been able to run the entire data set in Winsteps. When I try to run all the persons and items, it gives the error "invalid 'times' argument" in snowIRT or "missing value where TRUE/FALSE needed" for snowRMM. When I have entered a subset of items, then try to add extra items it will eventually give me one of the previous errors, or "arguments imply differing number of rows: " followed by two item labels.

hyunsooseol commented 4 months ago

Hi Matthew

In snowRMM or snowIRT usesna.omit( )to erase missing data. When I deleted missing data with your data, there is no available data to run analysis. Here is an result with R.

image

Kind Regards Seol