On 2/7/06, Mao Fan <[email protected]> wrote:
> Dear Stata users,
>
> I hope you are doing well all the time!
>
> I am writing a term paper about efficiency of futures market.
> However, I am not sure if I could resort to stata to do my econometric
> models. My goal is to test parameter hypotheses after Johansen's
> cointegration test.
>
> For example, I have two time series:
> spot price: St
> forward price: Ft
> The cointegration regression is like:
> St = a+b*Ft+et
>
> The efficiency of futures market requires that
> b = 1 and a is some constant (maybe storage cost) such that
> et = St - bFt - a is stationary.
>
> My questions are:
> (1) How to estimate a and b in Stata using Johansen cointegration test?
> (2) How to test if (a,b) = (0,1) after Johansen cointegration test?
>
Typing -findit johansen- reveals a number of hits.
I'm not an econometrician (nor do I work with time-series data), but
given your description perhaps the -vecrank- command will allow you to
perform the desired tests.
HTH's
Neil
--
"Never judge a book by its movie." - JW Eagan
Email - [email protected]
Website - http://slack.ser.man.ac.uk/
Blog - http://slack---line.blogspot.com/
Flickr - http://www.flickr.com/photos/slackline/
*
* 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/
