Dear Statalisters,
I need your advice on the following problem:
I want to compare the size off some specific teeth
between two groups (boys and girls). My dataset
consists of 6 (upper) and 6 (lower) teeth measurements
per individual in wide format for 100 boys and 100
girls. Let us suppose that all these measurements are
normally distributed given each individuals gender. Is
there a multiple comparison problem if one fits 12
regressions one for each teeth (eg xi:reg
tooth_size`i' i.gender, i=1 ... 12) or there is no
such a problem because all these test are not
independent. Is there any gain in using "mvreg" or
"sureg" commands ( I think that "mvreg" and "sureg",
given a common set of covariates, produce the same
results as separate regressions). Finally do you
believe that a hierarchical modeling approach (teeths
nested within individuals), using xtreg perhaps, is a
preferable solution. I am familiar with hierarchical
models but my prior experience is mainly on repeated
measurements of the same variable over time.
Any thoughts would be greatly appreciated.
Nikos Pantazis
Biostatistician
__________________________________
Do you Yahoo!?
Yahoo! Finance Tax Center - File online. File on time.
http://taxes.yahoo.com/filing.html
*
* 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/