Prof J C Nash (U30A)
2014-Dec-03 13:13 UTC
[R] non-finite initial optimization function; was "help"
If you want this resolved, you are going to have to provide the full function in a reproducible example. Nearly a half-century with this type of problem suggests a probability of nearly 1 that nlogL will be poorly set up. JN On 14-12-03 06:00 AM, r-help-request at r-project.org wrote:> Message: 14 > Date: Tue, 2 Dec 2014 12:38:03 -0300 > From: Alejandra Chovar Vera<alejandra.chovar at gmail.com> > To:r-help at r-project.org > Subject: [R] help > Message-ID: > <CAGW2UaDZYafdcnVYZ82qkb127FxRa0RVuv9z3MdVU1bp7mUAYg at mail.gmail.com> > Content-Type: text/plain; charset="UTF-8" > > Dear R > > I have a big problem in my estimation process, I try to estimate my > likelihood function with the option "optim", but R give me this message > "Error en optim(par = valores$par, nlogL, method = "BFGS", hessian = T, : > > valor inicial en 'vmmin' no es finito " I know this is because my initial > values are out the interval, but i try with different initial values and > the problem persist. > > I don't know what can i do. > > > I have this code, to obtain my initial values: > > > valores<- > optim(c(-1,-1,1,1,1),nlogL,method="SANN",control=list(maxit=1000)) > > DCp <- > optim(par=valores$par,nlogL,method="BFGS",hessian=T,control=list(maxit=1000)) > > > > I found in this link"http://es.listoso.com/r-help/2012-02/msg02395.html" > something similar, but in this case there isn't answer. > > > If you need more information about my code, please tell me. > > > Sincerely > > > Alejandra