<>
Does it mean, that if I have two negative coefficients and want to
test whether the one (which has the more negative point estimate) is
significantly more negative then the other, I can divide the p-value
by two and reject (or resepctively not reject) the null-hypothesis?
Yes. If the null is that the coefficients are equal (or, in one-tailed
terms, h0: \beta_1 >= \beta_2) then what you need to reject on a
one-tailed basis is that \beta_1 << \beta_2 in terms of the point
estimates. The p-val for that test is one-half the two-sided p-val
reported for a test of equality of the coefficients.
Kit Baum
[email protected]
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/