2SLS Error

[diggetybo]

Hello,

I'm going over a chapter in the book about 2SLS, and I've reproduced the books estimates the whole chapter except for the following problem:

Regress: (restricting the sample to {if inlf=1})

log(wage) c educ exper expersq

Educ is assumed to be endogenous and the IV of motheduc and fatheduc are used.

However when I put motheduc and fatheduc into the instrument list, it says insufficient instruments. Meanwhile the book's answer is as follows:

.048 + 061educ + .044exper -.009expersq

n=428, r2=.136

see attached file

Thank you

[EViews Gareth]

It would help if you told us which book...

But, at a guess, you need to include educ and educsq as instruments too.

[diggetybo]

It's the 2006 Wooldridge Economics. Chapter 15, example 15.5

Oh I got the right answer now, I was confused by the syntax. I thought Instrument list mean only IVs. To be honest, I'm not sure why that's why it works, does it have something to do with reduced form equations?

[startz]

The instrument list does mean only IVs, but sometimes a variable is both an instrument and a RHS variable.