[R] rate instead of scale in ?ks.test

Martin Maechler maechler at stat.math.ethz.ch
Mon Oct 3 09:31:37 CEST 2005


>>>>> "Ramon" == Ramón Casero Cañas <8-T at gmx.net>
>>>>>     on Sun, 02 Oct 2005 20:03:37 +0100 writes:

    Ramon> I am not sure whether I'm doing something wrong or
    Ramon> there is a bug in the documentation of
    Ramon> ks.test. Following the posting guide, as I'm not
    Ramon> sure, I haven't found this in the bug tracker, and
    Ramon> the R FAQ says that stats is an Add-on package of
    Ramon> R, I think this is the place to send it.

well "stats" is not exactly what we'd call an "Add-on package".
You cannot get an R installation without it.

    Ramon> ?ks.test provides the example

 Ramon> <QUOTE>

 Ramon> # Does x come from a shifted gamma distribution with shape 3 and scale 2?
 Ramon> ks.test(x+2, "pgamma", 3, 2) # two-sided

 Ramon> </QUOTE>


    Ramon> Maybe it should say ``with shape 3 and rate 2''?

Definitely.  You are right
{and there's a small history to the reason for this "typo",
 not really worth of our time though}. 

This is such a trivial bug fix that it can even be applied to
the code-frozen R 2.2 beta.

Thank you, Ramón!

Martin Maechler, ETH Zurich




More information about the R-help mailing list