VECM Entering Intercepts and Trends

Questions and discussions on Vector Autoregressions
dunt
Posts: 1
Joined: Sat Jul 30, 2011 12:10 pm

VECM Entering Intercepts and Trends

Unread post by dunt »

I am running a money demand model VECM model and wish to allow for an intercept in the cointegrating vector and for a linear trend in the VAR. The closest I can get to this is the following commands which appear to allow for an intercept and trend in the VAR but do not allow for an intercept in the cointegrating vector:

source(noecho) c:\winrats\johmle.src
@johmle(lags=2,det=trend, CV=CVECTOR)
# lrealM1 lrealGDP OC
equation(coeffs=cvector) ecteq *
# lrealM1 lREALGDP OC
system(model=ectmodel)
variables LREALM1 lREALGDP OC
lags 2
ect ecteq
end(system)
estimate

Can this be amended to include an intercept in the vector?
TomDoan
Posts: 7814
Joined: Wed Nov 01, 2006 4:36 pm

Re: VECM Entering Intercepts and Trends

Unread post by TomDoan »

The more recent versions of JOHMLE (the current one is at http://www.estima.com/forum/viewtopic.php?f=7&t=239) has the option DET=RC, which restricts the constant to the cointegrating vector. By constrast, DET=CONSTANT includes an unrestricted constant, which allows/produces a trend in the variables.
Post Reply