Re: hist and probability=T

[David L Lorenz <lorenz@usgs.gov>]

Vincent,
  They are probability densities.
For the first one, the gap is 0.05, so the sum of the counts times the
gap is equal to one. For the second one, the gap is 5, so the densities
are much smaller. Try varying the number of classes to see the effect on
counts when probability=T.
Dave

Furstoss <Vincent.Furstoss@lusignan.inra.fr>
Sent by: s-news-owner@lists.biostat.wustl.edu

09/04/2008 05:23 AM

Please respond to
Vincent.Furstoss@lusignan.inra.fr

To	snews <s-news@lists.biostat.wustl.edu>
cc
Subject	[S] hist and probability=T

Dear Splus user,

I am working with Splus Version 6.2.1  for Sun SPARC, SunOS 5.8, 64-bit
: 2004

and i am surprise with the results of the following command:

 > hist(rnorm(20, mean=.5,sd=.1), probability=T, plot=F)
$breaks:
[1] 0.35 0.40 0.45 0.50 0.55 0.60

$counts:
[1] 2 5 3 7 3

why counts are not probabilities ?

When the variable to display doesn't range between 0 and 1, the results
of counts
are probabilities:

 >  hist(rnorm(20, mean=.5,sd=.1)*100, probability=T, plot=F)
$breaks:
[1] 30 35 40 45 50 55 60 65

$counts:
[1] 0.01 0.02 0.01 0.04 0.03 0.05 0.04

Is there good reason for this ?

Many thanks for your answers.



-- 

 Vincent Furstoss



 fax: 05 49 43 93 72
 tel: 05 49 89 00 93



mailto:vincent.furstoss@lusignan.inra.fr


--------------------------------------------------------------------
This message was distributed by s-news@lists.biostat.wustl.edu.  To
unsubscribe send e-mail to s-news-request@lists.biostat.wustl.edu with
the BODY of the message:  unsubscribe s-news