Page 1 of 1

Keep data in MLwiN after model estimation to speed up subsequent modeling?

Posted: Tue Jul 13, 2021 9:41 pm
by erikruzek
Hi all,

I have been working with large data files (1+ GB) and it would be helpful for me to be able to keep the data in MLwiN to prevent the Stata to MLwiN data transfer that happens each time I fire off a model using runmlwin. Is it possible to avoid the data transfer step and keep my data in MLwiN while still using runmlwin (or R2MLwiN)?

I realize that I could just use MLwiN natively but I am not at all familiar with its syntax or facilities whereas I am quite familiar with Stata (and R) for all my data management, graphing, and reporting needs.

Thanks,
Erik

Re: Keep data in MLwiN after model estimation to speed up subsequent modeling?

Posted: Wed Jul 14, 2021 3:53 pm
by ChrisCharlton
Unfortunately this functionality it not available, as the command requires MLwiN to be in a predictable state before it fits each model. You can however use the viewfullmacro, savemacro or saveworksheet options of the command to extract the required syntax, or the worksheet used to fit the model in MLwiN to save yourself having to set the model up manually in MLwiN. You could then use these to fit the series of models directly in MLwiN, however you would also have to manually bring the results back to Stata if you wanted to do further analysis there.

Re: Keep data in MLwiN after model estimation to speed up subsequent modeling?

Posted: Wed Jul 14, 2021 4:47 pm
by erikruzek
Thanks for the quick response, Chris! I figured it was a longshot, but your proposed workaround is a good option.