The `theory' is about declining marginal returns
to X, or concavity, possibly with depreciation of
human capital producing an actual decline, but not
about a quadratic per se. The usual justification
of linear and quadratic terms is by analogy to
Taylor series, so you could put in higher order
terms, but not drop lower ones.
If you've got the log(age) in there, the quadratic
in log(age) has no such justification, unless
you've got some weird functional form assumptions.
Note that log(age) is already concave in age!
-----Original Message-----
From: Nick Cox [mailto:[email protected]]
Sent: Wednesday, November 10, 2004 4:57 PM
To: [email protected]
Subject: RE: st: RE: Quadratic term validity
I'll bow to knowledge here, naturally,
but
I still want to know if the quadratic follows
_deductively_ from plausible postulates,
or whether it just happens to be a convenient
functional form for theorists to play with.
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
