Uwe It looks like stop() in test files does not generate an error that is caught by Rcmd check on NT. Thus the fact that all the tests completed does not seem to mean too much. In Unix if the tests complete then there have not been stop()s generated by out of tolerance comparisons. This seems to mean that on NT all *.Rout files (50 or so) need to be examined to be sure that tests completed correctly. At the bottom of the crvB07.Rout file you sent you will see
if (! all.ok) stop("some tests FAILED")
Error: some tests FAILED Execution halted Perhaps you could grep for "Execution halted" in the *.Rout files to see if other tests failed. I am especially concerned about the tests in dse. The ones you sent from dseplus are numerically sensitive and the second one seems to have passed, so things look fairly good. (BTW, the values do seem to correspond more closely to Solaris than Linux.) Paul -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- 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 _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._