2
$\begingroup$

I'm trying to compare the model where asymptote value varies over subject and the one that does not. I've fit the first (the one that varies) but can't seem to figure out the latter.

The first one is

m1 <- nlmer(weight~ SSlogis(Time, Asym, xmid, scal) ~ Asym|Chick, cw1, start=c(Asym =400,xmid = 11, scal = 3))

For the second one I tried

m2<-nlmer(weight~ SSlogis(Time, Asym, xmid, scal), cw1, start=c(Asym =400,xmid = 11, scal = 3))
Error in as.call(nlform[[lnl <- length(nlform)]]) : invalid argument list

it seems that to use nlmer I HAVE to include a random effect part. Is there a way to fit nlmer with asymptote value fixed?

Thanks!!

$\endgroup$

1 Answer 1

2
$\begingroup$

you can't fit the second one because it is not a mixed effect model. There are no random effects. Try using the nls function to fit it.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.