[R] Add covariate in nlme?

[hwouters]

Hi all,

I solved my problem:
The reason for the error was that my initial values were not correctly
chosen.
In the previous code:
nlme.model001epr <- nlme(result ~ A0 * exp(- (   exp(A1) * exp(-Ea /
(0.0083144*TEMP.K))   *  exp(eps)) * time), 
                data = Parameterg, 
                fixed=list(A0+Ea~1,A1~Process), 
                random=eps~1, 
                start=c(93, 92, 34.5,*37,34*), 
                control=list(msVerbose=TRUE, maxIter = 200), 
                verbose=TRUE, method="REML", 
                na.action=na.pass) 
I have to use smaller values for the bold numbers: e.g.       start=c(93,
92, 34.5,*0.5,0.6*), 

Probably because the additional parameters are calculated based on what
should be added.

Best wishes,
Heidi


--
View this message in context: http://r.789695.n4.nabble.com/Add-covariate-in-nlme-tp4567189p4570242.html
Sent from the R help mailing list archive at Nabble.com.