www.cmm.bristol.ac.uk/forum

Dear all

I am using runmlwin to estimate models in MLwiN and export the results to Stata. While the runtime of the models in MLwiN is great, the speed of transmission back to Stata is rather slow. I suppose this is due to the fact that I need to include ~30 fixed effects.
Is there any way to increase the speed of MLwiN to Stata exporting?

Thank you very much in advance!

You could try using the mlnscript.exe file instead of mlwin.exe when calling MLwiN, as this will avoid setting up the GUI interface each time you call the software. The downside is that you won't be able to see the model equation, etc or fitting progress as the model runs.

Thank you for the suggestion and the quick reply. I am afraid using mlnscript.exe does not yield any noticeable improvement.
What slows the model is the time it takes to "export" the model results from MLwiN / mlnscript to the Stata output, i.e. for each coefficient D_Year2 D_Year3 (...) it takes a while to display the "row" before Stata moves on to the next "row". Given that there are many estimated (fixed) effects this becomes the biggest bottleneck.
...
D_Year2 .9250847 .0253249 -2.84 0.004 .8767568 .9760764
D_Year3 .9044179 .0569224 -1.60 0.110 .7994589 1.023157
D_Year4 .9004977 .057803 -1.63 0.103 .7940428 1.021225
D_Year5 .9923499 .0587488 -0.13 0.897 .8836336 1.114442
D_Year6 1.081647 .0616691 1.38 0.169 .9672864 1.209528
D_Year7 1.000614 .0412892 0.01 0.988 .9228747 1.084902
...

If you look at the runmlwin help via the following Stata command: You will see that there are a number of options for controlling the display under the Reporting options.

You may find that you can speed up the display by changing some of these (for example omitting the fixed-effects table).

Thank you for your reply and time, Chris, highly appreciated.