[R] Why do histogram bars vary their width?

[(Ted Harding)]

On 26-Dec-09 15:33:45, James Rome wrote:
> histogram(~(Arrival4) | as.factor(Hour), type="count",
> breaks=16,ylab="Arrival Count",
>   xlab="Arrival Rate/4",main="Friday EWR A22R D22L Configiration",
>   layout=c(6,4), par.strip.text=list(cex=0.7))
> 
> Why do I get plots with different bar widths? See attached.
> 
> Thanks,
> Jim Rome

Read the 'breaks' section under "Arguments:" in ?histogram
in the lattice package.

If you choose to use the default method:
  breaks = seq_len(1 + nlevels(x)) - 0.5
when 'x' is a factor, and
  breaks = do.breaks(endpoints, nint)
otherwise, or if you specify the numerical break-points explicitly,
as for instance in
  breaks = (0:15)
then the same set of break-points will be used for each histogram
across all panels. If you use another specification, such as yours:
  breaks=15
then:

  "Other values of 'breaks' are possible, in which case they
   affect the display in each panel differently."

which is what you are seeing. Compare the three histogram plots
from the following code:

  X <- c(rnorm(100),rnorm(50,1.0,0.5),rnorm(25,-1.0,0.5),rnorm(10))
  F <- factor(c(rep(0,100),rep(1,50),rep(2,25),rep(3,10)))
# The default:
  histogram(~X | F)
# Your choice (number of breaks)
  histogram(~X | F, breaks=10)
# Explicit specification of break-points:
  histogram(~X | F, breaks=0.5*(-6:6))

Hoping this helps,
Ted.

--------------------------------------------------------------------
E-Mail: (Ted Harding) <Ted.Harding at manchester.ac.uk>
Fax-to-email: +44 (0)870 094 0861
Date: 26-Dec-09                                       Time: 18:28:32
------------------------------ XFMail ------------------------------