Paul Bernhardt wrote:
>
> Reg Jordan wrote on 11/10/00 10:51 AM:
>
> >It's interesting that no Republicans have claimed that the ballot was
> >misleading -- all the complaints seem to come from Democrats. Wouldn't the
> >"misleading, confusing" nature of the ballot apply equally across the
> >voting spectrum?
>
> Bush was listed first on the ballot, and the hole to punch for him was
> also the first hole. So, no confusion if you wanted to vote for Bush. If
> you wanted to vote for Gore, the second name on the ballot, you had to
> punch the *third* hole on the ballot, the second hole being for Buchanan.
> Given the unexpectedly high number of votes for Buchanan in that county
> (3000 of about 400,000 votes cast) as in the next largest Buchanan county
> (Pinnelas (Tampa-Clearwater area), Buchanan got 1000 of the 400,000 votes
> cast). You have to argue that Palm Beach county has more conservatives
> than Pinnelas. If that's the case you would expect Bush to have done
> better in Palm Beach than Pinnelas. But, the oposite is the case. Palm
> Beach went decisively for Gore, while Pinnelas was very close to evenly
> split, with Gore leading only slightly.
Except that, curiously, the Bush-Gore split does *not* seem to be a
very good predictor of Buchanan vote. Plotting the log-transformed
proportion of Buchanan votes against the proportion of Bush votes:
-4.0+ *
- *
logPBpro - * *
- *
- P * * *
-5.0+ ** * * * * *
- * * * 2* *
- 2 * * * ** * *
- * * * * * *
- * * * 2 * *** *
-6.0+ * 2 * ** *
- * * *
- * * * *
- * * * *
-
-7.0+ *
-
--+---------+---------+---------+---------+---------+----Bushpro
0.320 0.400 0.480 0.560 0.640 0.720
The regression equation is
logPBpro = - 6.80 + 2.25 Bushpro
Predictor Coef StDev T P
Constant -6.8005 0.4440 -15.31 0.000
Bushpro 2.2484 0.7821 2.88 0.005
S = 0.5867 R-Sq = 11.3% R-Sq(adj) = 9.9%
There's an effect, but it's very much weaker than the relationship
between county size and Buchanan votes. Voting for Buchanan is
apparently a rural thing, not a classic left-right thing.
-Robert Dawson
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
