R help - Nov 2005 - breaks in hist()

Dear listers,

A quick question about breaks in hist().

The histogram is highly screwed to the right, say, the range of the vector is
[0, 2], but 95% of the value is squeezed in the interval (0.01, 0.2). My
question is : how to set the breaks then make the histogram look even?

Thanks in advance,

Leaf

Leaf:

An interesting question concerning graphical perception. As you have noted,
choice of bin boundaries in a histogram can have a big effect on how a
distribution is perceived. My $.02 (U.S.):

Histograms are a relic of manual data plotting. We have much better
alternatives these days that should be used instead. e.g.

1. (my preference, but properly not consumer-friendly). Plot the cdf instead
(?ecdf) .

2. Plot a density estimator (?density ; ?densityplot)

3. See David Scott's ash package, perhaps the KernSmooth package also
(though density() probably already has anything that you'd need from it). 

Cheers,

-- Bert Gunter
Genentech Non-Clinical Statistics
South San Francisco, CA
 
"The business of the statistician is to catalyze the scientific learning
process."  - George E. P. Box
 
 
> -----Original Message-----
> From: r-help-bounces at stat.math.ethz.ch 
> [mailto:r-help-bounces at stat.math.ethz.ch] On Behalf Of Leaf Sun
> Sent: Wednesday, November 02, 2005 9:49 AM
> To: r-help at stat.math.ethz.ch
> Subject: [R] breaks in hist()
> 
> Dear listers,
> 
> A quick question about breaks in hist().
> 
> The histogram is highly screwed to the right, say, the range 
> of the vector is [0, 2], but 95% of the value is squeezed in 
> the interval (0.01, 0.2). My question is : how to set the 
> breaks then make the histogram look even?
> 
> Thanks in advance,
> 
> Leaf
> 
>

Hi Leaf

The word "even" can be interpreted in several ways but I will give it
a
shot.
If you want to specify the breakpoints to represent the aggregation in your 
data you can use the argument breaks within histogram i.e.

x=c(runif(95,0,0.2),runif(5,.21,2))
hist(x, breaks=seq(0,2,.1), freq=F )#It will use breakpoints at 
0,0.1,0.2,...2

or you can also suggest a pre-defined number of cells i.e.
hist(x, breaks=7, freq=F )


You can also add a density line over the histogram using lines
lines(density(x, bw=.1))

Alternativelly, you can use some more basic visualization like a 
stem-and-leaf plot
stem(x)

I hope this helps

Francisco

>From: "Leaf Sun" <leaflovesun at yahoo.ca>
>To: "r-help at stat.math.ethz.ch" <r-help at
stat.math.ethz.ch>
>Subject: [R] breaks in hist()
>Date: Wed, 2 Nov 2005 10:48:45 -0700
>
>Dear listers,
>
>A quick question about breaks in hist().
>
>The histogram is highly screwed to the right, say, the range of the vector 
>is [0, 2], but 95% of the value is squeezed in the interval (0.01, 0.2). My 
>question is : how to set the breaks then make the histogram look even?
>
>Thanks in advance,
>
>Leaf
>
>______________________________________________
>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