Re: statistical study after next Tues election

From: Robert Rapplean <robert_at_rapplean_dot_net>
Date: Tue Nov 09 2004 - 09:55:01 CST

Hello, all. Every concept should be suspect in proportion to its
attractiveness. I'd hate to start a flame war over this, but I spent
much of yesterday afternoon doing some math, I don't believe that
Kathy's numbers reflect anything except the habit of southern democrats
to vote for Republican presidents. I projected the 2000 voting numbers
into 2004 numbers, adjusting for shifts in voter registration, and
compared the resulting number to the actual election numbers. The
pattern doesn't pan out. The shift in the op-scan distribution is
actually less than that in the e-voting machines.

Republican: 111.5% of projected with a of 8.8%
Democratic: 98.8% of projected with a std dev of 5.7%

Republican: 103.1% of projected with a of 16.1%
Democratic: 101.24% of projected with a of 8.1%

If you take just the larger half of the OpScan districts, you get:
Republican: 105.5% of projected with a of 9.6%
Democratic: 101.40% of projected with a of 6.5%

Here's a link to the complete explaination of the calculations, and all
of the numbers for all of the counties:

Please review them and make a decision about whether this forum is
appropriate to continue this discussion.

Kathy Dopp wrote:

>Edward Cherlin said:
>> (David Dill) and (Bev
>>Harris). Bev Harris has just filed the largest Freedom of
>>Information Act request in history to get the data from every
>>voting machine in the country.
>AWESOME. What did they ask for? What data from every voting machine?
>Will they be successful? Do you have a link to the story?

= The content of this message, with the exception of any external
= quotations under fair use, are released to the Public Domain
Received on Tue Nov 30 23:17:21 2004

This archive was generated by hypermail 2.1.8 : Tue Nov 30 2004 - 23:17:44 CST