[R] rnorm??

[Liaw, Andy]

I don't see anything suspicious (R 2.0.1 on Windows XP Pro, Pentium M):

> set.seed(1)
> res <- replicate(50, {x <- rnorm(1e6); c(sum(x < -4), sum(x > 4))})
> apply(res, 1, summary)
        [,1]  [,2]
Min.    20.0 21.00
1st Qu. 27.0 30.00
Median  30.0 33.50
Mean    30.7 33.74
3rd Qu. 34.0 37.00
Max.    42.0 48.00
> pnorm(-4) * 1e6
[1] 31.67124
> res2 <- replicate(50, {x <- qnorm(runif(1e6)); c(sum(x < -4), sum(x >
4))})
> apply(res2, 1, summary)
         [,1]  [,2]
Min.    18.00 19.00
1st Qu. 30.00 27.25
Median  32.00 31.00
Mean    32.60 31.38
3rd Qu. 35.75 35.00
Max.    47.00 45.00
> RNGkind()
[1] "Mersenne-Twister" "Inversion"       

Andy


> From: Scholz, Fritz
> 
> I am wondering whether there is a bug in rnorm.
> When generating rnorm(1000000) and counting 
> the cases > 4 and the cases < (-4) I get rather
> unexpectedly low counts for the latter. The problem goes away
> when using qnorm(runif(1000000)).
> 
> Fritz Scholz, PhD
> Applied Statistics Group
> Boeing Phantom Works
> fritz.scholz at pss.boeing.com
> 425-865-3623
> Tu/We 206-542-6545 (most likely)
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide! 
> http://www.R-project.org/posting-guide.html
> 
>