Re: OPE-L:_Wage_share (and gamma)

From: Allin Cottrell (cottrell@wfu.edu)
Date: Sat Sep 18 2004 - 23:44:48 EDT


Sorry, it took me a while to respond to this.

On Thu, 9 Sep 2004, Ian Wright wrote:

> Julian Wells is working on the distribution of the profit rate.
> According to Julian, some empirical measures are gamma, but many are
> not.

Do you know what sort of statistic Julian (or others) are using to
test the hypothesis that a given empirical distribution is a sample
from a gamma distribution?  I've done some searching on this but not
found anything very useful (the tests I have seen require that the
null hypothesis specifies the values of the gamma parameters.)

> In the social relations model the distribution can be approximated
> by a parameter-mix of ratios of normal variates with means and
> variances distributed according to a power-law. This is a
> 7-parameter distribution...

Gak!  Doesn't that sound like over-fitting?  Does Occam approve?

Allin Cottrell


This archive was generated by hypermail 2.1.5 : Mon Sep 20 2004 - 00:00:03 EDT