R help - Jun 2011 - packages which call functions which run C code...

I am looking at the function ks.test in the stats package and trying to
figure out why it gives a different result for a p-value than does the
corresponding function in MATLAB.  I am hoping for one of two responses:

 

1.       You know about ks.tests and have a familiarity with both the R and
MATLAB algorithms and can tell me why this should be happening.

2.       You know where I can find the C code so that I can decipher it.

 

Thanks,

-Steve Wolf


	[[alternative HTML version deleted]]

On Thu, Jun 23, 2011 at 4:46 PM, Steven Wolf <wolfste4 at msu.edu>
wrote:
> I am looking at the function ks.test in the stats package and trying to
> figure out why it gives a different result for a p-value than does the
> corresponding function in MATLAB. ?I am hoping for one of two responses:
>
>
>
> 1. ? ? ? You know about ks.tests and have a familiarity with both the R and
> MATLAB algorithms and can tell me why this should be happening.
>
> 2. ? ? ? You know where I can find the C code so that I can decipher it.
You can download the source R bundle (a .tar.gz or tar.bz, for example
http://cran.stat.ucla.edu/src/base/R-2/R-2.13.0.tar.gz), unpack it,
then navigate to the R source directory, go to subdirectory
src/library/stats/src and look at the file ks.c. The R function
ks.test is defined in src/library/stats/R/ks.test.R.

HTH,

Peter

On 2011-06-23 16:46, Steven Wolf wrote:
> I am looking at the function ks.test in the stats package and trying to
> figure out why it gives a different result for a p-value than does the
> corresponding function in MATLAB.  I am hoping for one of two responses:
>
>
>
> 1.       You know about ks.tests and have a familiarity with both the R and
> MATLAB algorithms and can tell me why this should be happening.
>
> 2.       You know where I can find the C code so that I can decipher it.
>
>

Go to

  https://svn.r-project.org/R/trunk/src/library/stats/R/ks.test.R

for the code of ks.test()

and to

  https://svn.r-project.org/R/trunk/src/library/stats/src/ks.c

for the relevant C code. Or download the source code from
your favourite CRAN mirror.

Peter Ehlers
>
> Thanks,
>
> -Steve Wolf
>
>
> 	[[alternative HTML version deleted]]
>
> ______________________________________________
> 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.