September 21, 2016

Hypothesis on the nature of this election: 1980 redux

Hackneyed pols often trot out the example of 1980 and Ronald Reagan as key to understanding the effect of debates.

In that election, RR was tied or trailing Jimmy Carter for months until the debates "showed" that RR wasn't a complete corpse on stage. It

assured the public (or so we are told) that Reagan was ready...and people fell in line to vote for him.

A lot of people have been presuming this to be the template for the current election...believing that HRC is carter and Trump is Reagan.

But what if this is wrong? Clinton's numbers are the most elastic: she passes 50% frequently in the polls, when not under press attack.

Trump NEVER does. People want to vote for her over Trump, but are concerned about the bad press she has gotten.

So maybe this means that people are waiting for a reason to get on board with Hillary. Maybe SHE is Reagan in this scenario.

Just a thought.

September 21, 2016

Trump has made essentially no progress in Wisconsin for months

Clinton has only slumped a bit. She wins this on turnout

September 21, 2016

New Hampshire Monmouth Poll

HRC 47
DJT 38
GJ 10
JS 1

Epic result.

We own the map now. Probably.

September 21, 2016

If Marquette's Wisconsin poll is good for Clinton I'll eat my hat

They have had Trump closing for weeks. Brace yourselves...incoming.

September 21, 2016

NC Poll by PPP: not a great result

Donald Trump 45
Hillary Clinton 43
Gary Johnson 6
Clinton/Trump head to head is tied at 47

This is not a "sick Hillary effect". Poll was Sunday-Tuesday.

NC will be a hard state to win.

September 20, 2016

Here is why 538's odds on Hillary are decreasing while The Upshot is increasing.

I knew this, but had put it out of mind. 538 aims to be a predictive model and in doing so it projects trends in horse race numbers forward in time. Today's polls by Monmouth and St. Leo in Florida both had larger leads for HRC way back in August. So todays lead for her is indicatrive of downward trend in her numbers. So her numbers, coupled with weirdo Reuters semi-polls, actually got WORSE.

Frankly, I think this methodology makes no sense. If you do believe in statistical momentum (and I'm not sure I do), incorporate it into your model using the agggregate horse race numbers, not individual polls. If you fit the trendlines to individual polls, you effectively penalize that poll for having drawn an outlier in the past. I can't see a rationale for that at all.

Fitting data in this manner will cause your model to jump around haphazardly, based on the coupling coefficients to each polls trendline, because the polls come at stochastic time. Using an aggregate trend over all polls makes more sense if you value consistency in a model.

Nate Cohn, at NYTimes Upshow seems to have noticed this as well, and I don't think he agrees with Silver based on his twitter timeline.

September 20, 2016

T+1 in North Caroline over Clinton's Hell Week

https://www.elon.edu/e/elon-poll/poll-archive/092016.html

Not bad. Very gettable.

Once the bad days shake out of everyone's samples, things are looking much rosier.

September 20, 2016

Ipsos poll of Ohio has HRC up +3

But Ipsos 50 state polling is very iffy. Take with grain of salt.

It's a two week window. Yikes.

September 20, 2016

Carson Wentz is gonna die.

Agree?

Disagree?

September 20, 2016

North Carolina poll coming tomorrow morning.

From Elon group. Their release on the senate race today in NC has Ross (D) up +1. That would make it hard to have Trump up by much if anything for the general.

However, the release does have McRory (R) up for governor. So that's kind of weird.