[R] ANOVA "ex post" Analysis

Thomas Lumley thomas at biostat.washington.edu
Mon May 10 20:33:42 CEST 1999

On 10 May 1999, Peter Dalgaard BSA wrote:

> ---------------------------------------------------------
> From:    Thomas Lumley <thomas at biostat.washington.edu>
> Date:    Tue Jul 14,  5:33pm -0700
> To:      Matthew Kay <mwkay>
> Here is code for three p-value based post hoc tests: bonferroni, holm, and
> hochberg. Holm is better than Bonferroni under all circumtances. Hochberg
> is more powerful than Holm, but under some slightly pathological
> situations it can exceed the nominal Type I error rate.
> I haven't looked at this code for a long time, but I think it works
> correctly. Refeerences for the methods are in "Adjusted p-values for
> simultaneous inference" by S. Paul Wright in Biometrics some time in
> the early 90s (I'm in the wrong country at the moment so I don't have the
> full reference).

 The reference is 
  author =       "S Paul Wright",
  title =        "Adjusted P-values for simultaneous inference",
  key =          "Biometrics",
  volume =       48,
  pages =        "1005--1013"

Thomas Lumley
Assistant Professor, Biostatistics
University of Washington, Seattle

r-help 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-help-request at stat.math.ethz.ch

More information about the R-help mailing list