[R] Post Hoc on repeated measures?

Peter Dalgaard BSA p.dalgaard at pubhealth.ku.dk
Fri Mar 2 14:19:36 CET 2001


Fredrik Karlsson <fredrik at ling.umu.se> writes:

> Hi all,
> 
> I'm a potential new user of R and have to know this before I start using it:
> SPSS does not let you do a Post Hoc analysis on repeated measures data.
> This is a problem for me, since that is what I will have to do.
> Will R let me do this? 

Not out of the box. It would certainly depend on what kind of repeated
measures model and what kind of post hoc test. The generic multiple
testing approach (p.adjust()) is always available if only you can find
the p-s to adjust.... Scheffe-style tests are also quite generally
available if you have a covariance matrix of the estimates for a given
effect. You'd have to write yourself, which shouldn't be too hard to
do. Doug Bates has (had?) a student working on related stuff.

Things like multiple range procedures generally have requirements on
the structure of the covariance matrix for the means, and would only
work under sphericity assumptions, I think.

-- 
   O__  ---- Peter Dalgaard             Blegdamsvej 3  
  c/ /'_ --- Dept. of Biostatistics     2200 Cph. N   
 (*) \(*) -- University of Copenhagen   Denmark      Ph: (+45) 35327918
~~~~~~~~~~ - (p.dalgaard at biostat.ku.dk)             FAX: (+45) 35327907
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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