I'm sorry to bother you with my question again, but something went wrong the
first time I sent it.
Hello, I�m currently working on my master thesis regarding the use of the yield spread
to predict future recessions on Norwegian data. To do this I�m estimating several
probit models of the form P(Yt=1|x)=F(b0+b1Xt-k),
where Y is a dummy variable which equals 1 in recession months
and 0 in non-recession months. X is the spread between 10 year government
zero coupon bonds and treasury bills with 3 (6, 9 or 12) months to maturity.
I would like to calculate robust standard errors adjusted for autocorrelation using the
Newey-West (1987) technique. I have downloaded the nwest function (STB-39 sg72),
and run the command (I am running Stata MP 10 and all files are up to date):
. nwest probit Rec_skj l12.sp_10_n12 if time>301 & time
_________________________________________________________________
Sjekk ut noen av de nye elektroniske tjenestene p� Windows Live Ideas�s� nye at de ikke engang har blitt offisielt utgitt enn�.
http://ideas.live.com
*
* 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/
