interpretation of Gregory Hansen structural break
Posted: Fri Jul 15, 2011 5:15 am
I am using eviews 6.0 and downloaded the subroutine to carry out Gregory-Hansen procedure for testing cointegration in the
case of regime shifts. The output of the subroutine consists of a ghz table and a ghc equation.I am using the ADF test
procedure and the ghc table provides the t-stat which I am comparing with the value provided in tha table 1 of the
Gregory-Hansen paper to decide whether to accept or reject the null hypothesis. the ghc equation provides the coefficient
of the estimated equation.
In many cases, the null is getting rejected which means that there is cointegration if the structural break is accounted
for. But when i look at the equation, the coefficients of the dummy variables are insignificant which suggests that there
is no structural break in the equation.
Please help me to interprete the result properly.
case of regime shifts. The output of the subroutine consists of a ghz table and a ghc equation.I am using the ADF test
procedure and the ghc table provides the t-stat which I am comparing with the value provided in tha table 1 of the
Gregory-Hansen paper to decide whether to accept or reject the null hypothesis. the ghc equation provides the coefficient
of the estimated equation.
In many cases, the null is getting rejected which means that there is cointegration if the structural break is accounted
for. But when i look at the equation, the coefficients of the dummy variables are insignificant which suggests that there
is no structural break in the equation.
Please help me to interprete the result properly.