[OPE-L:5625] Re: ope-l: RE: In defence of correlation

Allin Cottrell (cottrell@wfu.edu)
Tue, 21 Oct 1997 15:21:07 -0400 (EDT)

[ show plain text ]

On Tue, 21 Oct 1997, andrew kliman wrote:

> Again, I do not think that Paul's notion of "unbiased" is
> a meaningful one.

That there remains systematic variation in the residuals of
a regression of Y on X does not make X a biased predictor of
Y, as statisticians use the term. Bias would arise, for
instance, if one used value as a predictor of price while
the true relationship were

price = 1000 + .8*value + error

Allin Cottrell
Department of Economics
Wake Forest University