[R] feed cut() output into goodness-of-fit tests

[Phil Spector]

Andrei -
     Looking inside the code for cut, it looks like you could retrieve 
the breaks as follows:

getbreaks = function(x,nbreaks){
     nb = nbreaks + 1
     dx = diff(rx <- range(x,na.rm=TRUE))
     seq.int(rx[1] - dx/1000,rx[2] + dx/1000,length.out=nb)
}

The dx/1000 is what makes cut()'s break different than
a simple call to seq().


 					- Phil Spector
 					 Statistical Computing Facility
 					 Department of Statistics
 					 UC Berkeley
 					 spector at stat.berkeley.edu



On Fri, 15 Oct 2010, Andrei Zorine wrote:

> Hello,
> My question is assuming I have cut()'ed my sample and look at the
> table() of it, how can I compute probabilities for the bins? Do I have
> to parse table's names() to fetch bin endpoints to pass them to
> p[distr-name] functions? i really don't want to input arguments to PDF
> functions by hand (nor copy-and-paste way).
>
>> x.fr <- table(cut(x,10))
>> x.fr
>
> (0.0617,0.549]   (0.549,1.04]    (1.04,1.52]    (1.52,2.01]     (2.01,2.5]
>           16             28             26             18              6
>   (2.5,2.99]    (2.99,3.48]    (3.48,3.96]    (3.96,4.45]    (4.45,4.94]
>            3              2              0              0              1
>
>> names(x.fr)
> [1] "(0.0617,0.549]" "(0.549,1.04]"   "(1.04,1.52]"    "(1.52,2.01]"
> [5] "(2.01,2.5]"     "(2.5,2.99]"     "(2.99,3.48]"    "(3.48,3.96]"
> [9] "(3.96,4.45]"    "(4.45,4.94]"
>
>
> --
>
> Andrei Zorine
>
> ______________________________________________
> 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.
>