[R] Estimates at each iteration

Jonathan P Daily jdaily at usgs.gov
Fri Apr 8 17:57:37 CEST 2011

I'm assuming that English is not your first language. In light of that, I 
would suggest that you post your question in a language that we both 
speak: R. Please include:

1) E-step and M-step functions.
2) The proposed optim/maxLik call.

Mostly because (at least optim) does not have a parameter called 

Jonathan P. Daily
Technician - USGS Leetown Science Center
11649 Leetown Road
Kearneysville WV, 25430
(304) 724-4480
"Is the room still a room when its empty? Does the room,
 the thing itself have purpose? Or do we, what's the word... imbue it."
     - Jubal Early, Firefly

r-help-bounces at r-project.org wrote on 04/08/2011 08:16:36 AM:

> [image removed] 
> [R] Estimates at each iteration
> hello bye 
> to:
> r-help
> 04/08/2011 11:45 AM
> Sent by:
> r-help-bounces at r-project.org
> Dear Sir\ Madam
>  I am trying to maximise a complicated loglikelihood function  via 
> EM algorithm 
> which consists of two step "E-step and M-step"and in this case I need to 

> maximize the expected of like lihood function " which I get from E- 
step" and 
> take those estimates of parameter to update the E-step and repate these 
> convargence has been met. So I need to know if I control the number 
> of iterlim 
> in maxLik or optim Package by puting this number equals to one to 
> M-step and getting  just the estimates of parameter for one 
> iteration and hence 
> use them to update the E-step and again maximaize M-step by using maxLik 
> optim by contoling the number of limiter and putting the number equals 
to 1 
> is it true and acceptance? I mean if I do this my results can be 
> reasonable?. please I am waiting your response.
> Regards
> Fauzia Taweab
> phd.student.
>    [[alternative HTML version deleted]]
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide 
> and provide commented, minimal, self-contained, reproducible code.

More information about the R-help mailing list