nonlinear mixed model convergence problem

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

nonlinear mixed model estimation done with the original data set, but not converge with some selected sub data sets

any simple idea about how to solve? (using R built in nlme; and I've tried to change the initial value by using those estimated by nonlinear model without random effect, but not very effective)

Thanks.

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：mixed model Convergence Nonlinear converge nonlinea model Convergence problem Mixed Nonlinear

自己顶一下——赚钱买书

Was subset randomly selected cross the whole data?

yes, by nonparametric bootstrap. Thanks.

I only know about using Bootstrap to validate the model by picking up the random sample from original data file with replacement. Due to the nature of replacement, Bootstrap sample may cause the convergent problem, and that's why validation need to be done more times, say 100 times. Then it would give you robust measurements of  models from bootstrap subsets, and assess the variability of models' coefficient.  

So are you doing model validation ???

no, I'm doing model selection, but the idea is similar as validation, and I'm doing 10,000 times simulation with 80% of the original sample size without replacement

"nonlinear mixed model estimation done with the original data set, but not converge with some selected sub data sets"

Leaving 20% data out, is still validation process. Yes, it's part of the model selection.
Also if you are doing 10,000 times simulation, and as you said "not convergent with some selected sub-data sets"  if only "some" were not convergent, I don't think it is a major concern anways.
The reasoan to do the simulation is to assess the robustness of measurements of models' coefficients. If "some" not convergent, then it may tell that the models done using those subsamples were not robust enough to the true model.