A vaguer but more general answer is that there are lots of
ways of doing this, of which the Scheff� procedure is
just one, and much controversy about what is best, including
some scepticism about whether any such post hoc comparisons
are justifiable. "Multiple comparisons" is a key phrase
for further reading.
Nick
[email protected]
Herve STOLOWY
> You should add the option "scheffe" at the end of the
> -oneway- command.
>
> The theoretical syntax is the following:
>
> oneway response_var factor_var [if] [in] [weight] [, options]
>
> So, you would have:
>
> oneway response_var factor_var [if] [in] [weight], scheffe
claude francoeur
> I have 5 groups in my sample. I want to know if the mean of a
> continuous
> variable is different between those groups. I did a oneway
> Anova which tells
> me that there are differences between the groups. Now, I
> would like to
> compare the group means between each other. What is the
> appropriate test and
> what would the command be (or the right test under Stata's menu
> (Statistics/tests/...) ?
*
* 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/
