[R] Simulation with cpm package

[Uwe Ligges]

On 13.11.2012 15:45, Christopher Desjardins wrote:
> Hi,
> I am running the following code based on the cpm vignette's code. I believe
> the code is syntactically correct but it just seems to hang R. I can get
> this to run if I set the sims to 100 but with 2000 it just hangs. Any ideas
> why?

No: Works for me and completes within 90 minutes.

Uwe Ligges


> Thanks,
> Chris
>
> library(cpm)
> cpmTypes <- c("Kolmogorov-Smirnov","Mann-Whitney","Cramer-von-Mises")
> changeMagnitudes <- c(1, 2, 4, 5)
> changeLocations <- c(50,100,300)
> sims <- 2000
> ARL0 <- 500
> startup <- 20
> results <- list()
> for (cpmType in cpmTypes) {
>    results[[cpmType]] <- matrix(numeric(length(changeMagnitudes) *
>                                           length(changeLocations)), nrow =
> length(changeMagnitudes))
>    for (cm in 1:length(changeMagnitudes)) {
>      for (cl in 1:length(changeLocations)) {
>        print(sprintf("cpm:%s magnitude::%s location:%s",
>                      cpmType, changeMagnitudes[cm], changeLocations[cl]))
>        temp <- numeric(sims)
>        for (s in 1:sims) {
>          x <-c(rchisq(changeLocations[cl], df=3), rchisq(2000,
>
> df=changeMagnitudes[cm]))
>          temp[s] <-detectChangePoint(x, cpmType,
>                                      ARL0=ARL0,
> startup=startup)$detectionTime
>        }
>        results[[cpmType]][cm,cl] <- mean(temp[temp > changeLocations[cl]]) -
>          changeLocations[cl]
>      }
>    } }
>
> 	[[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at 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.
>