Reply #88: sampling error

[davidgmills]

First, other boards have mentioned the computer blackout and I thought the latest on that issue was that this turned out to be disinformation. Am I wrong?

Second, on the issue of fourth exit poll of the day being "corrupted" by actual polls, and the third poll of the day being "pure," Mystery Pollster and others have made the claim that this is the way exit polls have always been done and that doing it this time was not some nefarious act.

Again, I do not know.

Third, what I have always found interesting is that the difference in number of respondents between the third and fourth polls have been very few, making the difference between the published third and fourth exit poll results mathematically impossible, unless "corrupted" by the actual results.

But if the actual results are supposed to be part of the last phase of the process, then you would expect "mathematically impossible results" if the actual results differed widely from exit polls.

It would seem that somewhere, perhaps Germany or some other European country, we could find out whether final exit poll data should include actual results or should not. Of course Freemans' point was that when they do, they are useless as a check for predicting fraud. Some studies did just that.

My assumption would be that if they are used elsewhere as fraud predictors, they can not be corrutpted with actual results. We need to find out where.