Skip to content

bug ? wilcox() (PR#243)

2 messages · ATurpin@discoveriesinsight.org, Peter Dalgaard

#
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-devel mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-devel-request@stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
2 days later
#
ATurpin@discoveriesinsight.org writes:
This *was* a bug in older versions of ctest. Your example has a huge
number of cases with x==y and the test was based on 

	STATISTIC <- sum(r[x > 0])

(x being x-y at that stage) 

The current version at CRAN removes the zeros first...