Saturday, September 10, 2016

Why has Trump Gained in Polling Averages ?

Yesterday, the talk of the day was Democrats panicking (as always) because support for Trump is creeping up in polling averages (as are estimated probabilities of President Trump). Today's talk is totally deplorable and I will ignore it.

I think believe the shift (from mid August to early September 2016) is mostly due to which polls have dropped (there are clear house effects) and sampling error.

The reason is that it doesn't appear at all in the USA LA-Times panel poll.

They poll the same people again and again. They weighted so that self reported 2012 voting corresponds to actual 2012 votes. This means that they underweight people who claim they voted for Obama (systematically more claim to have voted for the winner than actually voted for the winner). This makes the level of the poll uninteresting.

But changes show how actual people have changed their minds, and are interesting

Look at Trump gaining uh ooops What ! In this panel poll of the same set of people, Clinton has gained from mid August to early September. The sample isn't huge, but the change isn't due to any change in the sample. People trying to explain what has happened have to deal with these data.

No comments: