Re: st: one sided t test, multiple coefficients

["Michael N. Mitchell" <Michael.Norman.Mitchell@gmail.com>]

Dear Ignacio

  If you are doing a test like

. regress y a b c
. test a b

  I am not aware of anything built into Stata that will formulate this as a one tailed 
test, given that it is testing an omnibus hypothesis

  Ho: Ba = 0, Bb = 0

  But it would seem that you could inspect the direction of the effect yourself and 
divide the alpha accordingly. But, I think that there are more sophisticated methods that 
have been published on this (I think Tukey wrote something on this).

I hope this helps,

Michael N. Mitchell
Data Management Using Stata      - http://www.stata.com/bookstore/dmus.html
A Visual Guide to Stata Graphics - http://www.stata.com/bookstore/vgsg.html
Stata tidbit of the week         - http://www.MichaelNormanMitchell.com



On 2010-09-24 10.51 AM, Andres Susaeta wrote:
> Hello Stat listers,
> It seems to be a simple question but I haven't been able to figure it
> out yet. I'm trying to perform a simple test for multiple coefficients
> (Wald test). Stata provides the test command to do it but it is a two
> side one. Is there any code for one tailed test for multiple
> coefficients?
>
> Ignacio
> *
> *   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/
*
*   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/