Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


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

st: Re: pwcompare


From   Janet Hill <janethill73@yahoo.co.uk>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   st: Re: pwcompare
Date   Fri, 25 Nov 2011 16:35:40 +0000 (GMT)

Why does pwcompare give different results after anova and xtmixed? Using the following syntax:
xtmixed lhist i.group##i.time || dog:, reml cov(id)
or
anova lhist group / dog|group time time#group, repeated(time)
followed by
pwcompare group, emptycells(reweigh) eff asbalanced post

I get the following for xtmixed
------------------------------------------------------------------------------
             |                            Unadjusted           Unadjusted
             |   Contrast   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
lhist        |
       group |
     2 vs 1  |  -.4591643   .5681373    -0.81   0.419    -1.572693    .6543643
     3 vs 1  |   1.200595    .525993     2.28   0.022     .1696677    2.231522
     4 vs 1  |  -.3857097    .525993    -0.73   0.463    -1.416637    .6452175
     3 vs 2  |   1.659759   .5681373     2.92   0.003     .5462306    2.773288
     4 vs 2  |   .0734546   .5681373     0.13   0.897    -1.040074    1.186983
     4 vs 3  |  -1.586305    .525993    -3.02   0.003    -2.617232   -.5553775
------------------------------------------------------------------------------
and for the anova
------------------------------------------------------------------------------
             |                            Unadjusted           Unadjusted
             |   Contrast   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
       group |
     2 vs 1  |  -.4591643   .1047385    -4.38   0.000    -.6722564   -.2460723
     3 vs 1  |   1.200595    .096969    12.38   0.000      1.00331     1.39788
     4 vs 1  |  -.3857097    .096969    -3.98   0.000    -.5829947   -.1884248
     3 vs 2  |   1.659759   .1047385    15.85   0.000     1.446667    1.872851
     4 vs 2  |   .0734546   .1047385     0.70   0.488    -.1396375    .2865467
     4 vs 3  |  -1.586305    .096969   -16.36   0.000     -1.78359    -1.38902
------------------------------------------------------------------------------

I can see that the standard errors are different, but the question arises should I use xtmixed or anova for repeated measures?

I am using Stata 12.0, update 10 Nov 2011.

Thanks,
Janet

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index