Welcome to European Tribune. It's gone a bit quiet around here these days, but it's still going.
What's the relevance?

Maybe if the hypothesis is that there was vote reversal in a single county, the odds to calculate is of Obama ahead only in 3. But I don't think such a calculation is realistic by using a binary variable (Obama ahead/Clinton ahead).

*Lunatic*, n.
One whose delusions are out of fashion.

by DoDo on Wed Jan 16th, 2008 at 06:26:13 PM EST
[ Parent ]
This is difference from the question of who's ahead. It's the question of which direction the machine effect goes. There are counties in which the machines don't change the lead, but here I'm looking at how many times the machines favour obama or Clinton (regardless of whether it is by enough to change the lead). In fact, the lead only changes in 3 out of the 10 counties. But to study the odds of the lead changing you need a model of the average lead and the variability of the vote, so it is no longer a nonparametric test.

We have met the enemy, and he is us — Pogo
by Migeru (migeru at eurotrib dot com) on Wed Jan 16th, 2008 at 06:30:30 PM EST
[ Parent ]


Top Diaries

Occasional Series