R help - Aug 2011 - density function cannot work well on UNIX R version 2.13.

Hi, there,
 
I found density function?cannot work well on UNIX.R
version 2.13.1 (2011-07-08), Platform: i386-pc-solaris2.10 (32-bit)

Here is an example from R doucments which can work well on other version.

plot(density(c(-20,rep(0,98),20)), xlim = c(-4,4))# 
 
But right now the estimated probablity =0 for all point.
 
Do I need do something about float point?

Thanks.
Alex

On Aug 31, 2011, at 1:04 PM, alex46015 at yahoo.com wrote:
>
> Hi, there,
>
> I found density function cannot work well on UNIX.R
> version 2.13.1 (2011-07-08), Platform: i386-pc-solaris2.10 (32-bit)
>
> Here is an example from R doucments which can work well on other  
> version.
>
> plot(density(c(-20,rep(0,98),20)), xlim = c(-4,4))#
What do you get with just this:

  density(c(-20,rep(0,98),20))

Here's what we are seeing:

Call:
	density.default(x = c(-20, rep(0, 98), 20))

Data: c(-20, rep(0, 98), 20) (100 obs.);	Bandwidth 'bw' = 1.019

        x                    y
  Min.   :-2.306e+01   Min.   :0.000e+00
  1st Qu.:-1.153e+01   1st Qu.:1.125e-12
  Median :-1.776e-15   Median :6.311e-06
  Mean   :-1.593e-15   Mean   :2.167e-02
  3rd Qu.: 1.153e+01   3rd Qu.:1.884e-03
  Max.   : 2.306e+01   Max.   :3.828e-01

 > density(c(-20,rep(0,98),20))$y[
             which.min(abs( density(c(-20,rep(0,98),20))$x ) )
                                 ]
[1] 0.382816
>
> But right now the estimated probablity =0 for all point.
That is not what the rest of us are seeing.
>
> Do I need do something about float point?
>
> Thanks.
> Alex
>
> ______________________________________________
> 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.
David Winsemius, MD
West Hartford, CT