Re: [Gretl-users] tsls tests
Doh!
I should've thought of that. You're right of course. If I run a model dropping
experience altogether, and instrument for ed76, smsa76 and south76, the Hausman test has
df = 3.
I'm still confused about the 0.0 critical values in the weak instruments test
though...
PS
-----Original Message-----
From: gretl-users-bounces(a)lists.wfu.edu [mailto:gretl-users-bounces@lists.wfu.edu] On
Behalf Of Allin Cottrell
Sent: Wednesday, April 21, 2010 2:14 PM
To: Gretl list
Subject: Re: [Gretl-users] tsls tests
On Wed, 21 Apr 2010, Allin Cottrell wrote:
On Wed, 21 Apr 2010, Summers, Peter wrote:
> I'm still not sure about the df in the Hausman test though. In
> the last model it seems to me that this should be 2, not 1...
I will take another look at that.
You still have perfect collinearity in the relevant respect. The
issue is that in the Verbeek schooling dataset the experience
values are "fake" (as is quite often the case in labor-market
datasets); they are calculated numbers representing "potential
experience", as in
exp76 = age76 - ed76 - 6
This means that when you run the unrestricted regression for the
Hausman test one of the "hat"-variables gets dropped
automatically, leaving just one degree of freedom for the test.
Allin
_______________________________________________
Gretl-users mailing list
Gretl-users(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users