R devel - Mar 2006 - Logic Error (PR#8677)

Full_Name: Matthew Davis
Version: 2.2.0
OS: OS X (10.4.5)
Submission from: (NULL) (209.107.120.195)


the mean of my sample x is 0.2, and when I check mean(x)<=0.2 I get a TRUE
value, when I check mean(x)<=(1-0.8) I get a FALSE value.  (x <- c(0, 1,
0, 0,
0, 1, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0))

> 0.2==(1-0.8)
[1] FALSE

On Mar 12, 2006, at 15:39 , mkdavis at math.ucalgary.ca wrote:
> Full_Name: Matthew Davis
> Version: 2.2.0
> OS: OS X (10.4.5)
> Submission from: (NULL) (209.107.120.195)
>
>
> the mean of my sample x is 0.2, and when I check mean(x)<=0.2 I get  
> a TRUE
> value, when I check mean(x)<=(1-0.8) I get a FALSE value.  (x <- c 
> (0, 1, 0, 0,
> 0, 1, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0))
>
> ______________________________________________
> R-devel at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-devel
>
==Jan de Leeuw; Distinguished Professor and Chair, UCLA Department of  
Statistics;
Editor: Journal of Multivariate Analysis, Journal of Statistical  
Software
US mail: 8125 Math Sciences Bldg, Box 951554, Los Angeles, CA 90095-1554
phone (310)-825-9550;  fax (310)-206-5658;  email: deleeuw at stat.ucla.edu
.mac: jdeleeuw ++++++  aim: deleeuwjan ++++++ skype: j_deleeuw
homepages: http://gifi.stat.ucla.edu ++++++ http://www.cuddyvalley.org
   
------------------------------------------------------------------------ 
-------------------------
           No matter where you go, there you are. --- Buckaroo Banzai
                    http://gifi.stat.ucla.edu/sounds/nomatter.au

On 3/12/2006 6:39 PM, mkdavis at math.ucalgary.ca wrote:
> Full_Name: Matthew Davis
> Version: 2.2.0
> OS: OS X (10.4.5)
> Submission from: (NULL) (209.107.120.195)
> 
> 
> the mean of my sample x is 0.2, and when I check mean(x)<=0.2 I get a
TRUE
> value, when I check mean(x)<=(1-0.8) I get a FALSE value.  (x <- c(0,
1, 0, 0,
> 0, 1, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0))
Why make this so complicated?  The natural conclusion from that is that 
0.2 is not equal to (1-0.8), and indeed:

 > (1-0.8) == 0.2
[1] FALSE

The problem is that neither 0.2 nor 0.8 can be represented exactly, so 
when you do calculations using them you are doing approximations.  The 
approximation involving your mean is different than the one involving 
(1-0.8).  This is an FAQ,

7.31 Why doesn't R think these numbers are equal?

This is not a bug.

Duncan Murdoch