[R-sig-ME] lme4/nlmer problem

[Markus Jäntti]

Kalle Eerikäinen wrote:
> Hello,
> 
> I have done some test estimations using the lme4 package of R. The 
> estimation of the parameters of linear mixed-effect models using the 
> 'lmer' goes well. For instance, a very simple single-level mixed model 
> "Naslund_lmer1  <- lmer(y ~ d13 + (1 |stand), data = height1)" for the 
> relationship between the tree height (or its transformation) and 
> diameter comes out perfectly.
> 
> However, if I attempt to estimate nonlinear mixed-effect models, I 
> always receive an error message that tells me: "Error: 
> length(start$fixed) is not TRUE". This is also the case with the 
> following model:
> 
> Schumacher_nlmer1 <- lme4:::nlmer(ht   ~ exp(p0 + p1*1/d13)+u0 ~ 
> (u0|stand) , fixed=p0+p1~1, data = height1, start = c(p0 = 0.1, p1 = 
> -9.0), verb = 1)

What is the purpose of the argument "fixed=p0+p1~1"? The help page makes no 
mention of it. Maybe this is what is generating the error message.

markus
> 


> It is obvious that there exists a trivial bug/mistake in my code, but I 
> cannot see what is wrong with it. Could someone give me a helping hand 
> with my 'nlmer problem'?
> 
> Regards,
> 
> Kalle Eerikäinen
> 
> 
> ------------------------------------------------------------------------
> 
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models


-- 
Markus Jantti
Abo Akademi University
markus.jantti at iki.fi
http://www.iki.fi/~mjantti