[R] seg fault

[Lorenz Gygax]

Dear all,

sorry for the confusion I caused regarding the subject "segmentation
fault". The corrections that made it to the list were corrections of a
mail that bounced (because of its lengths). I included too much data
because I thought that my problem was connected with the exact
distribution of it. This does not seem to be the case as I found out with
some help from Martin.

Well, the problem is that I get a segmentation fault calling loess. It
seems to be a problem of the lengths of the variables included in loess. 
Is there an upper limit of points that can be treated using loess? It
seems so (see the example at the end). 

More generally, is there a way to find out what actually caused a
segmentation fault?

Regards, Lorenz

example:

library ("modreg")
n <- 1000
while (TRUE) {
  cat (n, "\n")
  .Random.seed <- 0:3
  x <- runif(n)
  y <- 3 + 4*x + rnorm(n)/10

  loess(y ~ x, span= 1)
  n <<- n+500
}

1000 
1500 
2000 
2500 
3000 
3500 

Process R segmentation fault at Fri Mar  5 15:53:42 1999




-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._