st: Using prtest for large obs, in conjunction with oneway

[Steven Young <youngazn@gmail.com>]

I am a bit new to statistics. I have a sample of about 2400 with 3
variables, each with 2 or 3 levels associated with them. As I was
reading online, I saw that z-tests should be used in favor of t-tests
when n>30. After finding that prtest is the z-test equivalent, I
proceeded to use it.

I have been using .oneway to check for equal variance in the
population, and then had continued to conduct a t-test. If I found
that Bartlett's chi2 was significant, I rejected the equal variance H
and used unequal welch with my ttest. Do I need to do the same when
using prtest, ie run .oneway to check for equal variance? Or would I
forgo that and just compare the data with prtest alone?

Although the documentation also says bitest is preferable, it does so
by mentioning "smaller" samples. Reading the documentation on bitest,
it seems to be more useful for actual probability values, whereas I
have data means to test. What do you say?

Thank you.

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