Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: wald test, one-sided test not appropriate


From   "Scharnigg, Stan (Stud. SBE)" <s.scharnigg@student.maastrichtuniversity.nl>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   st: wald test, one-sided test not appropriate
Date   Tue, 7 Jun 2011 19:48:15 +0200

Dear statalisters,

I have the following regression:

regress var1 var2 var3, 
where var1, var2, var3 are B1, B2, B3 respectively.

Hypothesis:
H0: B1 + B1 + B1 >= 0

Someone told me that I could use a Wald test to test this. I used the FAQ: http://www.stata.com/support/faqs/stat/oneside.html
then, I did the following:

regress var1 var2 var3
local sign_var1 = sign(_b[var1])
local sign_var2 = sign(_b[var2])
local sign_var3 = sign(_b[var3])
display "Ho: coef >= 0  p-value = " 1-ttail(r(df_r),`sign_var sign_var2 sign_var3'*sqrt(r(F)))

However, at the end of the page there is written:
"Again, this approach (performing a Wald test and using the results to calculate the p-value for a one-sided test) is appropriate only when the Wald F statistic has 1 degree of freedom in the numerator"

My degrees of freedom is 3 in this case. So, this test is not appropriate. 
Why is it not appropriate and how could I solve this? 

Thank you very much


*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index