Re: [Gretl-users] Test reverse causality
Am 10.04.2014 11:04, schrieb andrea_conti_86(a)tiscali.it:
Dear Gretl users,
i'm doing panel regression where i suppose there's a reverse causality
among independent and dependent variables and I can't find instrument
for them .
Does exist a test that tell me if such reverse causality exists?
If I understand your description of the problem correctly, especially
the non-existence of suitable instruments, then you indeed have a
problem, because a standard test of endogeneity of the regressors would
be based on such instruments.
However, if you're already pretty sure that the instruments are invalid,
aren't you equally sure that indeed there is "reverse causality"? If so,
why do you still need to test? (Half-serious question.)
-sven