xtdpdml

[Hazel Pettifor]

I am running xtdpdml using stata 14.2, a bivariate random effects model (with no lags at this stage) but cannot get convergence. The basic model is as follows:

xtdpdml lnBeh lnlcCogs , tfix ylags(0) skipcfatransform skipconditional re

The data is panel (20 year time frame (n=483)). I have tried unsuccessfully reducing the data to 5 waves. Does anybody have any experience of this model and could recommend a fix? Thanks

[Richard Williams]

Generic suggestions for dealing with convergence problems are at

https://www3.nd.edu/~rwilliam/xsoc73994/L02.pdf

if that doesn’t help, if you are free to send me you data I can look at it in a few days. I am the co-author of xtdpdml.

[Hazel Pettifor]

Hi Richard. Thank you very much for replying. I've already looked at your paper and can't find a fix. It would be great if I could send the data over to you. Thank you very much again.