Polling Updates

We had a couple of new polls come out this week in the competitive states.  I want to start off and explain how the margin of error works and what typical errors are.  The margin of error is calculated based on a variety of assumptions (independence of observations, identically distributed probabilities, and no sampling error) that I don’t believe always hold.  So the margin of error doesn’t explain all of the error inside of a poll.  FiveThirtyEight analyzed polling error and found an (weighted) average error of 5.4 for Senate elections for polls 21 days before the election.  An average error works like a standard deviation in interpreting error.  This has an interpretation of a poll being about plus or minus 10.8% the expected mean about 95%.    But since the election is far away and it is a midterm year, we should expect a little higher error in the polls right now, so anything within 5-10 points is still somewhat realistic for the other candidate.  But with multiple polls combined the errors get exponentially smaller.

In West Virginia,  a new poll shows Manchin with a 10 point lead.  This combined with multiple other polls suggests this race is not competitive and the one poll with a Morrisey lead was an outlier.  I am no longer considering the West Virginia as a competitive race.

In Arizona, a set of polls on 7/9, focused on the Republican Primary candidates.  McSally was in the lead,  and she had the best poll numbers against the presumed Democratic nominee.  This seat is currently held by Senator Flake who is retiring.

A Missouri poll shows a Republican primary candidate,  Josh Hawley, ahead of Senator McCaskill.  I am not sure if Hawley will win the primary, but this poll shows that the race is competitive.

In Montana, the race is still looking close.  A new poll had Tester with a 3 point lead.  This is 5 points closer than the last poll,  but all or most of this difference could easily be explained by sampling error.  Rosendale (R) will have to appeal more to moderate and independent voters to win.

In Tennessee, a poll shows the presumed Democratic Senate nominee and former Governor Bredesen with a 6 point lead over the presumed Republican nominee Blackburn, a US Representative.

In Florida,  a new poll showed Senator Nelson with a lead of 4 points against Rick Scott (current Governor of Florida), technically outside the margin of error. The polls have been going back and forth.  The polls are over different periods of times, use different polling methods, and are by different pollsters,  which means it’s not unusual that they are different.  My guess is that right now the result would be between +4 for Nelson and +4 for Scott.  The primary is coming up soon,  and after that more people might decide even though Nelson (D)  and Scott (R) are the only viable candidates.

These changes along with the other changes from last week mean the competitive races are now:  Arizona, Nevada, Tennessee, Florida, Missouri, Montana, North Dakota, Ohio, Michigan (temporarily until primary), Wisconsin (temporarily until primary).  I know that one poll has a large error, but when you see multiple large leads without external evidence for a close race the odds of the polling being wrong to get smaller.  In my model competitiveness matters because it determines the prior which can affect the final call.  I want my groups to be as homogenous as possible.

 

 

The Role of the Supreme Court Confirmation in the 2018 Midterm Elections

Today I want to discuss the role of the Supreme Court nomination in the competitive Senate races I am following.

I’m especially interested in how the Democratic incumbent senators in states Trump won will vote.  Ultimately, I think  Kavanaugh will get confirmed before the election so his confirmation may no longer be a direct issue in November.  However,  how the senators voted could definitely still be on voters minds.  It’s probably a lose-lose situation  Vote no and you may have just created a new attack ad and alienated Trump supporters and conservative,  but vote yes and alienate independents and your parties leadership.  I wouldn’t be surprised if some of these candidates will be considering the effects this vote could have on their reelection.  I’m am particularly interested in Heitkamp from North Dakota and Tester from Montana since both of them are in tight races in places where a conservative Supreme Court justice might be popular.

I am going to remove a few states I previous named as competitive,  because the polling data doesn’t support a close race.  I am no longer considering the Texas race competitive after a 5th poll shows Cruz with a study lead.  O’Rouke may do very well for a Democrat in Texas,  but I just don’t think the polls support a competitive race.  Pennslyvania and Ohio are now considered safe for the Democratic candidate, and Wisconsin and Michigan will be considered safe for the Democratic candidate after there primary unless the Republican nominee has a poll with the Republican Candidate winning outside of the margin of error.  On August 1,  races will be recategorized depending on whether or not they have at least 1 post-primary poll showing a within margin error lead.

 

North Dakota Race Profile and Polling Update

Polling Updates

Two new Texas polls show Cruz is still leading.  One showed Cruz +5 and the other was Cruz +10.  Both were outside the margin of error. These polls were from 6/8 to 6/17 for the 5 point lead and 6/19 to 6/22 for the 10 point lead.  Given the child separation controversy occurred around this time,  that might have affected these numbers.  O’Rouke still needs to improve his numbers.

A new Nevada poll shows the Rosen,  the Democratic challenger,  with a 4 point lead that is technically outside of the 3.9% margin of error.  This is promising but it could just be a temporary bump from the backlash over child separations.

A new Pennsylvania poll shows that Casey has a safe lead.  Based on this and the other polls Pennsylvania has been moved to the safe blue column until further notice.

Similarly to Pennsylvania, another Ohio poll shows the incumbent Brown with a solid double-digit lead.  Therefore I am no longer considering Ohio a competitive race.

Two new contradictory Florida polls continue to a close race between the incumbent Nelson and the presumed Republican challenger Scott.  Scott has no competitors with a reasonable chance so he will probably be nominated.

North Dakota

2016 Presidential Election result:  Trump: 63%,  Clinton 27.2%, Margin: Trump +35.8%

2012 Senate Election result: Heitkamp (D) 50.2%,  Berg (R) 49.3%,  margin +0.9 D

Democratic Candidate: Heidi Heitkamp

Heitkamp was elected to the Senate in 2012 and was the Attorney General and Tax Commissioner of North Dakota before she was elected to the Senate.   She looks like a pretty moderate Democrat that has a pretty high Trump score for a Democrat in a state Trump won by a landside.

Republican Candidate: Kevin Cramer

Cramer has been a US representative since 2012,  and held other various political positions before then.   Cramer appears to be a populist Republican with Trump-like positions on his website.

My Thoughts on the Race:

The polls show a race that is close with one poll showing Heitkamp with a 3 point lead that was taken in February, and a more recent June poll shows Cramer with a 4 point lead which I am more inclined to view as accurate since pre-primary polls usually have undecided voters that will likely change their mind to their typical party once the primary is over.  Cramer just announced before the poll, so voters probably didn’t have enough information to decide.  Hopefully, there will be more polling before election day,  but this seat looks like it might flip to the Republican party.  Heitkamp barely won in 2012,  and Trump did well in North Dakota.

And as always,  for full disclosure, I am a moderate Republican,  and while I try to keep my politics out of my analysis,  they may affect how I view things.