Reply #48: and the price of tea in China?

[foo_bar]

Skids laid out his methodology:

Number of EIRS reports for Florida, Broward County:
Kerry votes changed:

To Bush: 11
(038775,022524,041745,042578,046528,047099,055055,055066,055396,053430,044658)
To Unspecified: 5 (041979,042530,046762,055080,001096)
To Brown: 2 (046394,056831)
To Nader: 1 (047606)
To writein: 1 (055103)

Bush votes changed:
To Kerry: 1 (048034)

So we have far more potential outcomes than a binomial distribution can express (remember, "mutually exclusive" and "dichotomous"). You can't get around the fact by dropping data points that don't fit your conclusion:

Trimming, according to Babbage, would essentially be the act of forcing observations to fit a desired mean by removing portions of those data points that deviate in excess and adding these portions to those data points that deviate in the other extreme. Babbage defined cooking as the process of making many measurements and then only reporting those choice measurements that are deemed satisfactory by the appropriate standards.

http://www.csu.edu.au/learning/eis/ethix_1.html

Intentionally dropping data points that disconfirm the hypothesis counts as falsification, a type of research misconduct. Some methods for ensuring that outliers are irrelevant and not disconfirming instances include repetition of the experiment, checking the calibration of instruments or of measurements. Unexpected data points may also indicate conclusions very different from what the researcher expects.

http://www.ori.hhs.gov/education/products/montana_round1/professional.html

versus...

That's why I stick with Zogby and ARG, etc. I've stopped blindly incoporating the latest poll that Votemaster puts up - unless t makes sense. Call me a cherry-picker. I throw away the bad ones. That's why my numbers seem so far out there for Kerry.

http://www.democraticunderground.com/discuss/duboard.php?az=show_topic&forum=132&topic_id=1039319#1041539

No, I leave them out because they are BIASED for Bush.

Why include them if they skew the averages against Kerry?

http://www.democraticunderground.com/discuss/duboard.php?az=show_topic&forum=104&topic_id=1998204#1998844