[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: Re: one-tail test
On Oct 11, 2004, at 2:33, Levy wrote:
Presuming that the test statistic is of the positive persuasion, divide
the reported p-value in half. E.g.
How can i perform a one sided test after a linear regression?
after this regression
regress y x1 x2
i want to test if the coefficient of x2 is greater than 0
headroom | -659.463 484.5101 -1.36 0.178 -1625.788
This test would be insig. at 10% level or better as a two-tailed test,
. di ttail(74,1.36)
indicates that a t of this (absolute) magnitude would allow us to test
that the coeff is negative with a significance level of 91+%, that is,
signif. at ten percent level as a one-tailed test.
Kit Baum, Boston College Economics email@example.com
* For searches and help try: