[Rd] Bug in nortest cvm.test package (PR#8980)

[Uwe Ligges]

rpowell at horizonenv.com wrote:

> I believe there to be a bug in the cvm.test module of the nortest  
> package authored by Juergen Gross. I do not know how to contact the  
> author directly.

What about typing
  library(help=nortest)
It reveals the address at once. Please send the report to the package 
maintainer.

Please do not send bug reports on contributed packages to R-bugs!

Uwe Ligges



> I've been running some normality tests using the nortest package. For  
> some of my datasets the Cramer-von Mises normality test generates an  
> extremely high probability (e.g., 1.637e+31) and indicates normality  
> when the other tests do not. I don't believe the generated  
> probability should exceed a value of "1".
> 
> Below are the results of the tests and then, below that, I've  
> provided the column of the datafile that results in the high value.
> 
> Sincerely,
> Bob Powell
> 
> Robert M. Powell
> Senior Project Scientist/Project Mgr.
> Horizon Environmental Corporation
> Suite 1700, Fisher Building
> 3011 W. Grand Blvd.
> Detroit, MI 48202
> Tel	(313) 874-0124
> Fax	(313) 874-0135
> Cell	(248) 977-0317
> http://www.horizonenv.com
> 
[SNIP]