[R] computing the average response by nlme

Spencer Graves spencer.graves at pdf.com
Sat Mar 25 02:49:46 CET 2006

	  Did you get an answer to this post?  I didn't see a direct answer, 
but I saw a related discussion around the time of your post.

	  In case you still would like help with this, I recommend you first 
consult Pinheiro and Bates (2000) Mixed-Effects Models in S and S-Plus 
(Springer) if you haven't already.  Also, I just got 93 hits from 
RSiteSearch("nlme predict").  Beyond that, the documentation for nlme 
says it returns an object of class "nlme".  This suggests you try 
method(class="nlme"), which identified the following functions with 
methods specifically for objects of class "nlme":

formula.nlme* getData.nlme* predict.nlme* update.nlme*
   Non-visible functions are asterisked

	  You can further get the code for "preduct.nlme" using 
getAnywhere("predict.nlme");  you can't get it directly, because as the 
message indicates, it's "non-visible".

	  hope this helps.
	  spencer graves
Marc Bernard wrote:

> Dear All,
>   let E(Y | t, b, theta) be the conditional  expectation of Y where b is a vector of random effects , theta is a vector of  fixed effects and t is the  time of observation (t =1,2, ...,n). 
>   I wonder if nlme has a function to compue E(Y | t, theta). I know that it can be done by approximating the integrals over b of   E(Y | t, b, theta). But I am wondering if nlme has a function to do that directly.
>   Thank you,
>   Bernard
> ---------------------------------
> 	[[alternative HTML version deleted]]
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html

More information about the R-help mailing list