Harold,
Obviously the bottleneck is your objective function fn(). I have speeded up
your function by a factor of about 2.4 by using `outer' instead of sapply. I
think it can be speeded much more. I couldn't figure it out without spending a
lot of time. I am sure someone on this list-serv
#opt <- optim(startVal, fn, method = "BFGS", hessian = TRUE)
> opt <- nlminb(startVal, fn)
> #opt <- Rcgmin(startVal, fn)
> opt
> #list("coefficients" = opt$par, "LogLik" = -opt$value,
> &quo
opt
#list("coefficients" = opt$par, "LogLik" = -opt$value,
"Std.Error" = sqrt(diag(solve(opt$hessian
}
dat <- replicate(20, sample(c(0,1), 2000, replace = T))
r2 <- pl2(datat, Q =10)
-----Original Message-----
From: Prof J C Nash
ow.
For a one-off computation, that may still be acceptable.
JN
On 15-02-18 06:00 AM, r-help-requ...@r-project.org wrote:
> Message: 37
> Date: Tue, 17 Feb 2015 23:03:24 +
> From: "Doran, Harold"
> To: "r-help@r-project.org"
> Subject: [R] multiple paramet
I am trying to generalize a working piece of code for a single parameter to a
multiple parameter problem. Reproducible code is below. The parameters to be
estimated are a, b, and c. The estimation problem is such that there is one set
of a, b, c parameters for each column of the data. Hence, in
5 matches
Mail list logo
