Slight differences in fitted coefficients in lme4_1.0-6 compared to lme4_0.999999-2
On 14-02-07 03:34 PM, Tom Wenseleers wrote:
Dear all, I noticed that I get very slight differences in my current lme4 1.0-6 models compared to the old ones I obtained earlier using lme4_0.999999-2. I was just wondering whether it would somehow still be possible to reproduce the output of the old lme4_0.999999-2, by setting appropriate options of the optimizer to use etc? Or is this not possible? I also tried installing the old lme4 version using install_url in package devel, but if I try this I get a complaint that the old version doesn't work with R.0.2. Any easy way to go back to the old version (I need this to be able to fully reproduce published results)?
I think you should be able to install lme4.0 from http://lme4.r-forge.r-project.org/repos/ to reproduce previous outputs. You *might* be able to reproduce previous results by setting control=lmerControl(optimizer="optimx",optCtrl=list(method="nlminb")), but I don't think we could guarantee that -- too much of the internal machinery has changed too radically. Ben Bolker
Cheers, Tom [[alternative HTML version deleted]]
_______________________________________________ R-sig-mixed-models at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models