On Nov 16, 2009, at 7:43 AM, Rafael Moral wrote:
Dear useRs,
I wrote a function that simulates a stochastic model in discrete time.
The problem is that the stochastic parameters should not be negative
and sometimes they happen to be.
How can I conditionate it to when it draws a negative number, it
transforms into zero in that time step?
Here is the function:
stochastic_prost <- function(Fmean, Fsd, Smean, Ssd, f, s, n, time,
out=FALSE, plot=TRUE) {
nt <- rep(0, time)
nt[1] <- n
for(n in 2:time) {
nt[n] <- 0.5*rnorm(1, Fmean, Fsd)*rnorm(1, Smean, Ssd)*exp(1)^(-(f
+s)*nt[n-1])*nt[n-1]}
if(out==TRUE) {print(data.frame(nt))}
if(plot==TRUE) {plot(1:time, nt, type='l', main='Simulation',
ylab='Population', xlab='Generations')}
}
The 2 rnorm()'s should not be negative; when negative they should
turn into zero.
...*max(0, rnorm(1, Fmean, Fsd)*max(0, rnorm(1, Smean, Ssd)*...
Thanks in advance,
Rafael
____________________________________________________________________________________
[[elided Yahoo spam]]
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
David Winsemius, MD
Heritage Laboratories
West Hartford, CT
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.