An embedded and charset-unspecified text was scrubbed... Name: not available URL: <https://stat.ethz.ch/pipermail/r-sig-ecology/attachments/20130113/d8aae09f/attachment.pl>
population simulations in R
5 messages · Peter Houk, Duncan Golicher, Roman Luštrik +1 more
An embedded and charset-unspecified text was scrubbed... Name: not available URL: <https://stat.ethz.ch/pipermail/r-sig-ecology/attachments/20130113/77897cf6/attachment.pl>
Hello Peter, It should be easy to adapt this to your needs. http://duncanjg.wordpress.com/2008/03/12/disturbance-and-the-lotka-volterra-competition-model/ All the best, Duncan
On Sun, Jan 13, 2013 at 11:40 AM, Peter Houk <peterhouk at gmail.com> wrote:
Greetings all -
I'm in the process of fitting some population models and had a question
regarding the simulation process in R. Below I've pasted a simple code for
logistic growth with some stochasticity in the growth rate parameter ("r" -
see the runif part of the code). If you run continue to repeat this code
you get a similar, but distinct and unique population model (i.e., graph of
population versus time) each time. What I'm figure out is how to automate
the process to do this say...10 times...and plot all ten simulations on one
graph. I'm trying to use a matrix approach, and fill each element.
However, I'm having difficulties figuring things out.
I appreciate any assistance offered,
Peter
Code:
test.logistic<-function(alpha=0.01, r0=1.2, f=0.2, N0=80, t=100) {
r<-c(r0, numeric(t))
for (i in 1:t) r[i+1]<- {
runif(1,0.8,1.1)
}
N<-c(N0, numeric(t))
for (k in 1:t) N[k+1]<- {
(N[k]+r[i]*N[k]*(1-(N[k]*alpha))-f*N[k])
}
return(N)
}
Nts<-bevholt()
t<-100
plot(0:t, Nts, type="l")
--
Peter Houk, PhD
Chief Biologist
Pacific Marine Resources Institute
www.pacmares.com
www.micronesianfishing.com
[[alternative HTML version deleted]]
_______________________________________________ R-sig-ecology mailing list R-sig-ecology at r-project.org https://stat.ethz.ch/mailman/listinfo/r-sig-ecology
Dr Duncan Golicher Investigador Titular, El Colegio de la Frontera Sur, Chiapas,Mexico Mexico tel +52 1 967 137 94 20 Skype name duncangolicher Publications: http://www.mendeley.com/profiles/duncan-golicher Senior lecturer, Bournemouth University, UK Centre for Conservation Ecology & Environmental Change School of Applied Sciences Christchurch House rm C218a Bournemouth University Fern Barrow Poole (Dorset) BH12 5BB UK Tel. +44 (0)1202 961682 For list of publications see Researcher ID: http://www.researcherid.com/rid/B-4240-2009 dgolicher at bournemouth.ac.uk dgoliche at ecosur.mx Researcher ID: http://www.researcherid.com/rid/B-4240-2009
An embedded and charset-unspecified text was scrubbed... Name: not available URL: <https://stat.ethz.ch/pipermail/r-sig-ecology/attachments/20130113/e6398c65/attachment.pl>
Hi,
I would do it like follows and I don't expect that the for loop should
be a performance problem here ;-)
Tomas P.
logistic <- function(x0, r, t) {
xx <- matrix(0, nrow = length(t), ncol = length(x0))
xx[1, ] <- x0
for (i in t) x0 <- xx[i, ] <- x0 + r * x0 * (1 - x0)
xx
}
nruns <- 100
time <- seq(1, 15)
r <- runif(nruns, 0.8, 1.1)
x0 <- rep(0.01, nruns)
system.time(
xx <- logistic(x0, r, time)
)
matplot(time, xx, type = "l", pch = ".", ylim = c(0,2))