tag:blogger.com,1999:blog-6698298.post1876863821427109256..comments2023-03-16T12:11:56.318+00:00Comments on David Hugh-Jones: lme false convergencedavidhughjoneshttp://www.blogger.com/profile/01123256773062047048noreply@blogger.comBlogger10125tag:blogger.com,1999:blog-6698298.post-39849796096834728392013-08-07T12:59:56.574+01:002013-08-07T12:59:56.574+01:00Hmm, well in that case I wonder if this is the rig...Hmm, well in that case I wonder if this is the right problem. But it might be; if so, then I guess you need to create appropriate dummy variables and multiply or divide by some amount. Awkward but it should still work.davidhughjoneshttps://www.blogger.com/profile/01123256773062047048noreply@blogger.comtag:blogger.com,1999:blog-6698298.post-75806247329972050152013-08-06T21:46:16.677+01:002013-08-06T21:46:16.677+01:00Oh, I apologize. Let me clarify. The independent v...Oh, I apologize. Let me clarify. The independent variables are categorical factors (treatment, sex, breeding condition). How can I correct for this problem? Thanks!Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6698298.post-79771675617132898862013-08-01T13:16:39.660+01:002013-08-01T13:16:39.660+01:00Almost surely your dependent variable will not be ...Almost surely your dependent variable will not be the problem - it will be one of your indep vars that is causing the problem.davidhughjoneshttps://www.blogger.com/profile/01123256773062047048noreply@blogger.comtag:blogger.com,1999:blog-6698298.post-12579207480180802992013-08-01T00:00:55.812+01:002013-08-01T00:00:55.812+01:00Will this solution work for lmer with binomial dat...Will this solution work for lmer with binomial data with a yes/no response? If so, I don't see how I can just divide the variable by 10, 100, etc. Please help.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6698298.post-14951592717250977992013-04-12T15:21:46.519+01:002013-04-12T15:21:46.519+01:00I had already spent quite a while with the same pr...I had already spent quite a while with the same problem on lme and this trick worked :)...saved my day and my weekend, many thanks!Eveliina Kallioniemihttps://www.blogger.com/profile/07592645069941510174noreply@blogger.comtag:blogger.com,1999:blog-6698298.post-49301590120969295172013-03-05T16:33:38.448+00:002013-03-05T16:33:38.448+00:00Thanks for this tip! It worked for me too, with th...Thanks for this tip! It worked for me too, with the added bonus that it makes sense to me!Yael Kiselnoreply@blogger.comtag:blogger.com,1999:blog-6698298.post-9228726801988352282013-02-01T23:06:18.285+00:002013-02-01T23:06:18.285+00:00Thanks for that tip, it was really helpful and wor...Thanks for that tip, it was really helpful and worked wonders for me too. Attempted to fit quadratic and cubic terms for age and encountered the same problem. I was including them using poly() but it was making the model coefficients difficult to interpret. Marie Galligannoreply@blogger.comtag:blogger.com,1999:blog-6698298.post-27184805772046060572010-07-02T14:18:42.400+01:002010-07-02T14:18:42.400+01:00I think the reason is that the numerical algorithm...I think the reason is that the numerical algorithm doesn't cope well if numbers get very large/small.davidhughjoneshttps://www.blogger.com/profile/01123256773062047048noreply@blogger.comtag:blogger.com,1999:blog-6698298.post-20759972147233198382010-07-02T13:35:19.823+01:002010-07-02T13:35:19.823+01:00This should probably be mentioned in the lme4 help...This should probably be mentioned in the lme4 help. If anyone is still following up here, why exactly does this work so well? I mean is there a logical/numerical/statistical reason that I'm not grasping?<br /><br />For now it's a mystery to me but it sure does work wonders. I've literally spent days both recently and in the past worrying about overfitting and whatnot, never being able to pinpoint the problem, and all along the solution was this simple.<br /><br />So thank you Dr. Hugh-Jones!Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6698298.post-9766089480797761592010-02-10T22:11:32.349+00:002010-02-10T22:11:32.349+00:00Thanks David! I was scouring the many R listservs ...Thanks David! I was scouring the many R listservs for a solution to this issue, and this was the only one that worked.Matt Goldrickhttps://www.blogger.com/profile/16614188116031906824noreply@blogger.com