Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: tukey/dunnett procedures

From   Steven Samuels <>
Subject   Re: st: tukey/dunnett procedures
Date   Tue, 14 Jun 2011 21:57:30 -0400


In Theresa Boswell's dunnett.ado (-findit-), there is a section:
        /* Call oneway and save mse and df */
        qui oneway `resp' `fact' if `touse',missing 
        local mse = r(rss)/r(df_r)
        local df = r(df_r)
If you can substitute the proper values of the MSE and degrees of freedom from your nested ANOVA command and meet the other requirements of -dunnett- (e.g. equal numbers per group), I think that will do it. Perhaps you can supply the same numbers to -princomp- or -smileplot-.


Steven J. Samuels
Consultant in Statistics
18 Cantine's Island
Saugerties, NY 12477 USA
Voice: 845-246-0774
Fax:   206-202-4783

On Jun 14, 2011, at 10:49 AM, Richard Goldstein wrote:

On Jun 14, 2011, at 2:47 PM, Roger Newson wrote:

I think you'll find that the Dunnett multiple-test procedure is really the Sidak multiple-test procedure. This is available using the -smileplot- package, downloadable from SSC. And the corresponding frequentist q-values are available from the -qqvalue- package, also downloadable from SSC.

I hope this helps.

Best wishes


Roger B Newson BSc MSc DPhil
Lecturer in Medical Statistics
Respiratory Epidemiology and Public Health Group
National Heart and Lung Institute
Imperial College London
Royal Brompton Campus
Room 33, Emmanuel Kaye Building
1B Manresa Road
London SW3 6LR
Tel: +44 (0)20 7352 8121 ext 3381
Fax: +44 (0)20 7351 8322
Web page:
Departmental Web page:

Opinions expressed are those of the author, not of the institution.

On 14/06/2011 15:49, Richard Goldstein wrote:
> hi,
> I am looking for any programs, or advice, on doing post-hoc Tukey and
> Dunnett procedures in Stata following a nested ANOVA command
> I am familiar with Gleason's -prcomp- command but it cannot handle nesting
> thanks,
> Rich
> *
> *   For searches and help try:
> *
> *
> *
*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index