Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: comparisons of sample data with published table data (immediate ANOVA)


From   Laurel.Copeland@med.va.gov
To   statalist@hsphsun2.harvard.edu
Subject   st: comparisons of sample data with published table data (immediate ANOVA)
Date   Sun, 13 Jul 2003 09:14:33 -0500

I am interested in comparing some study data I have with some published
data. Both studies have five groups of decedents -- sudden, cancer, organ,
frail, other.  Is there an extension of ANOVA that will let me compare ages
of these groups?  I find -contrasi-, which seems to do a one-way comparison
among the ages (given the Ns, means, and SDs), e.g.,
 contrasi 495 73 7.2 \ 1571 77 4.2 \ 1185 80 6.8 \ 3376 83 5.5 \ 631 83 7.0
 contrasi 1279 74.3 4.1 \ 6369 76.8 6.4 \ 4478 79.0 6.6 \ 2423 79.8 6.7
\1533 79.1 7.0
or, similarly, there is -aovsum-
 aovsum, n(495 1571 1185 3376 631) m(73 77 80 83 83) sd(7.2 4.2 6.8 5.5 7.0)
and I can put all 10 groups in at once, but the comparison between studies
is not evident because there are no post hoc pairwise comparisons.  Should I
do five immediate t-tests (-ttesti-) and then adjust for simultaneous
comparisons?  Or should I stick to unquantified observations ("the ages of
the groups in the two studies appeared to be similar...")?  Or--?
Thank you,
Laurel
Laurel A Copeland, PhD
VA Ann Arbor Health System
(734) 769-7100 x6206

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   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   |   What's new   |   Site index