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

Re: test: changing significance levels


From   Richard Williams <Richard.A.Williams.5@nd.edu>
To   statalist@hsphsun2.harvard.edu
Subject   Re: test: changing significance levels
Date   Thu, 24 Mar 2005 14:50:44 -0500

At 02:24 PM 3/24/2005 -0500, Yvonne Capstick wrote:
I apologize for such a simple question. I am using the "test" command to test for equality of coefficients under an F-test, having just performed a regression. Is there any way of either:

a) changing the command to test that one coefficient is greater than the other (i.e. specifiy a one-sided alternative hypothesis)
b) specifying a different signficance level than 5%. Unlike for other commands, an option ", sig" does not seem to be available for "test".

I've tried "help test" but it hasn't listed anything that can help.
1. Look at the coefficients and see if the difference is in the hypothesized direction. If so, then

2. Take the reported probability and divide by 2. e.g. if it says Prob > F = .06, the one-tailed probability is .03.

*
* 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