R help - Mar 2010 - Problems if optimization

What's up fellows...

I am a begginer in R and i am trying to find the parameters of one
likelihood function, but when i otimize it, always appers a error or
advertisement and the solve does not occur.
The problem seems like that:

 "lMix<-function(pars,y){
beta1<-pars[1]
beta2<-pars[2]
beta3<-pars[3]
beta4<-pars[4]
beta5<-pars[5]
alfa1<-pars[6]
Fsp<-log(1/(1+exp(beta1*y[,10]+beta2*y[,3]+beta3*y[,3]+beta4*y[,5]+beta5*y[,6]+alfa1*y[,11])))
Frp<-log(1/(1+exp(beta1*y[,10]+beta2*y[,3]+beta3*y[,3]+beta4*y[,5]+beta5*y[,6])))
logl<- sum((y[,15]*Fsp)+(y[,19]*Frp))
return(-logl)
}
optim(c(1,1,1,1,1,1), llMix, y=Mix, method="CG")
Erro em optim(c(1, 1, 1, 1, 1, 1), llMix, y = Mix, method = "CG") :
  Função não pode ser calculada nos parâmetros iniciais
optimize(c(1,1,1,1,1,1),llMix,y=Mix, method="CG")
Erro em min(interval) : invalid 'type' (closure) of argument
optim(llMix,pars=c(0,0,0,0,1,1),y=Mix, method="CG")
Erro em optim(llMix, pars = c(0, 0, 0, 0, 1, 1), y = Mix, method =
"CG") :
  cannot coerce type 'closure' to vector of type 'double' "
What is it happen?
Any one can fix it for me or give me suggestions?

I have also tried the maxLik package and it does not make the first
interaction on the maximization process.

Thanks a lot,
Gildemir

	[[alternative HTML version deleted]]

Francisco Silva wrote:
> 
> ....
> I am a begginer in R and i am trying to find the parameters of one
> likelihood function, but when i otimize it, always appers a error or
> advertisement and the solve does not occur.
> The problem seems like that:
> 
>  "lMix<-function(pars,y){
> 
> 
Shouldn't that be llMix?

I tried this:

llMix <- function(pars,y) {   
    beta1 <- pars[1]
    beta2 <- pars[2]
    beta3 <- pars[3]
    beta4 <- pars[4]
    beta5 <- pars[5]
    alfa1 <- pars[6]
    Fsp <-
log(1/(1+exp(beta1*y[,10]+beta2*y[,3]+beta3*y[,3]+beta4*y[,5]+beta5*y[,6]+alfa1*y[,11])))
    Frp <-
log(1/(1+exp(beta1*y[,10]+beta2*y[,3]+beta3*y[,3]+beta4*y[,5]+beta5*y[,6])))
    logl <- sum((y[,15]*Fsp)+(y[,19]*Frp))
    return(-logl)
}

Mix <- matrix(data=4*runif(25*19)+10,ncol=19) 
pstart <- c(1,1,1,1,1,1)
llMix(pstart,Mix)
optim(pstart, llMix, y=Mix, method="CG", control=list(trace=2))

And this works, in the sense of no error messages.
Something wrong with your data?

Berend
-- 
View this message in context:
http://n4.nabble.com/Problems-if-optimization-tp1692193p1692411.html
Sent from the R help mailing list archive at Nabble.com.