Looks interesting! Shoot!

At 3:35pm Nov 9th, with 2935 respondents, trump is up 1%.


So they made up 320 respondents in order to change the results??

Is "adjusting" the polls actually making up responses??


““We will know shortly after the polls close,” Lenski said. “We’ll have individual precinct results from all
the locations where we conducted interviews, so we’ll know how much understatement or
overstatement for the candidates we have. Our calls are based on all the information we have at the
time – exit polls, returns from sample precincts and county results from AP – and we may re-weight the
exit poll results later in the evening to match the vote estimates by geographic region.”

My brain just does not work that way. I need someone who will assume my number crunching ability is stuck in grammar school to explain it to me.

the peak of the dome is the most likely outcome, which is the actual vote matching the exit polling data. it is also likely that the exit polling is off by .1% or .2%. Right? Math tells us (by analyzing margins of error in the exit polling data) what a reasonable deviation from the exit polling data would be. If you look at figure 3, the author has made this + or - 2.5%. Meaning that if exit polls said Clinton 50.5%, it is reasonable to assume her actual total will be between 48% and 53%. He calls this the 95% confidence interval. This means that if the election were held 100 times, that 95% of the time Hillary's total would be somewhere in that interval (48% to 53%).

Her actual total of 47.6% falls outside this interval, meaning it is highly unlikely that the exit polling data was that far off.

That being said, there are 50 states, so the concept of a state being outside the confidence interval is not only believable, it is probable. The problem though is that several states are falling outside this confidence interval, meaning that "the odds of this happening are 5%" event is having many times, which is highly improbable. imagine you have 5 white balls and 95 red balls in a bin, and one at a time, you keep drawing white balls but no red ones. pretty unlikely right? The data is basically showing that white balls keep being drawn.

Just kidding. I appreciate the summary and understand. Thanks!

There could be a bias if provisional ballots are thrown out later. I doubt the exit polls asked if the voter voted provisional.

Then the pollster would be confident of matching the election result to within the margin of error 95% of the time.

When the poll and the vote count are outside the margin of error it means there is almost no chance at all that randomness can explain the deviation. There has to be another explanation. One possibility is the vote result is not true. The other possibility is to polling is defective. When you compare 2004 and 2016, you have to ask why would the same polling methods suddenly produce double the error.



Same states with the same Senate races and the same pollster using the same methods, but in 2012 they are off by twice as much plus the greatest error is in Republican-dominated states. In states with Democrats in the Secretary of State position, the election results and polling match much better. In states where the republicans were losing by the widest margins in the polls, the exit polling shows the largest red shift. The red shift even matches how much the election had to swing for Republicans to win.

In the graph above, if the trendlines were flat and matched zero, the exit polls would all be averaging precise and red/blue states would not bias the result. What we have instead is a pronounced red shift in almost every state. The odds of that happening are astronomical.

The battleground states had the most robust polling. This is seen in the match to the pre-election polling. What are the odds all those many polls are also off by the same amount?

A wise gambler would bet the election was rigged if they knew the truth could be shown. A wise politician knows that once an election is successfully stolen, there's about zero chance of proving it, we are just left with these exit polls for solace.

Which is how we end up with this graph, surgically precise electoral college theft does not alter the national trend:

where exit polls were done.

Last edited Thu Dec 8, 2016, 10:28 AM - Edit history (2)

There were exit polls in only 29 states, I believe. All the battleground states and states with Senate races. This is a change from past elections, when all states were polled.

The number of respondents varies by state, the battleground is reliable and the less contested states have far fewer respondents, both in exit polls and pre-election pooling. Note in the comparative graph above how close the polls are to each other in the battleground states. Again, what are the odds that dozens of averaged polls and the exit polls are all wrong and the election results are true? Astronomical. Billions to one this is not the result of randomness.

or in the final tallies. But seems machines can't be examined.

This election was stolen

Last edited Fri Dec 9, 2016, 06:49 PM - Edit history (1)

Thanks for the update

Republicans better finally get around to reading that book - The Bible - that they like to claim is their guide in ethics.