[EM] ossipoff tries to define "bias" for apportionment

Warren Smith wds at math.temple.edu
Wed Jan 24 15:21:27 PST 2007


("Bias measures--There really are no two ways about it")

the trouble is, according to this defintion, Ossipoff's "unbiased" methods
are biased.  That is because we can set up the hypothetical country to
violate his conditions.

Right?
wds



More information about the Election-Methods mailing list