Barrel Strength

Over-Proof Opinion, Smoothly Aged Insight

Barrelstrength year-end exchange over data, Hillary and Trump

In which the contributors to BS and friends of the contributors discuss data analytics

Dramatis Personae:

Arran Gold, numbers guy; Rebel Yell, chief scientist; Duke of Toronto, financial doomist; Dalwhinnie, Tory squire and Avatar of Enlightenment.

Arran Gold started it by sending the following article to the BS list. It went as follows:

How Analytical Models Failed Clinton

Her campaign was so confident in its data that it opted not to do tracking polls in states that decided the election.

The Novem­ber elec­tions pit­ted Demo­crats against Re­pub­lic­ans, con­ser­vat­ives against lib­er­als, Trump-style pop­u­lists and tea parti­ers against the es­tab­lish­ment and con­ven­tion­al politi­cians. An­oth­er con­test, fol­lowed mainly by polit­ic­al afi­cion­ados, matched tra­di­tion­al poll­sters against newly fash­ion­able ana­lyt­ics wiz­ards, some of whom—pre­ten­tiously in my opin­ion—called them­selves “data sci­ent­ists.”

It was well known that tra­di­tion­al polling was hav­ing prob­lems. The numb­ing ef­fect of bil­lions of tele­market­ing calls and the ad­vent of caller ID and voice mail had re­duced re­sponse rates (the per­cent­age of com­pleted in­ter­views for every hun­dred at­tempts) from the 40s a couple of dec­ades ago to the high single di­gits. As they struggled to get truly rep­res­ent­at­ive samples, poll­sters “weighted” their data more than ever be­fore, mak­ing as­sump­tions of what the elect­or­ate would look like on elec­tion days that were weeks, months, or even a year or more away.

You can read the rest of the article at the hyperlink. It offered a view of  the election what was beside the point, as if any improved techniques could have saved Hillary.


Dalwhinnie responded:


I am sure Rebel Yell and his statistician William Briggs will have something to say about this. For my part, the bias of this report is that better numbers could have told Clinton something and would have helped her make better decisions about ad-buys.

No. This election was not won or lost on polls directing ad-buys.

In an important  sense, this article doesn’t “get it”. Clinton lost because pride went before a fall, because Democratic votes are excessively concentrated in urban areas , and enough people voted in the right states in the right proportions for Trump to win, and that was because they had someone to believe in.

This is just more shouting at the bar.

Arran Gold responded in his characteristically polite way:

She never went to Wisconsin. The best explanation I have seen is that Putin put a cloaking device on that state so her campaign never saw it. She did go to Arizona and there was even talk of her taking Texas. That is just dumb.

That article was written by Charlie Cook of Cook Political Report who is non-partisan so there is no “get it” because his job is to analyze political campaigns. Is HRC a born loser, yes, but what should she have done differently? That is the question Cook is addressing.


He added:

Here is another example of Clinton’s approach being wrong.

Hillary Clinton’s Vaunted GOTV [ get out the vote ] Operation May Have Turned Out Trump Voters
A focus on big data over people may have backfired.


Clinton-was-gonna-lose-anyways doesn’t address the question on how to improve on a data driven campaign strategy next time around.


Rebel Yell then interposed:

Basically, the Clinton campaign believed their own bullshit about the voters.  And Trump. Big mistake.
Never assume away the capabilities of the enemy. The Clinton campaign outspent, out-organized and out-everything else the Trump campaign, but they still lost because it wasn’t about that.  It was about motivated voters getting to polls and doing it big time for Trump. If you get 30,000 people to rallies all over the country and have another 10,000 lined up waiting to get in, then that should tell you something.
As far as the polls go, the decline and fall of supposed whizz-kid Nate Silver should be a lesson to all.  He was totally wrong about Trump right up to election day and into the evening. Professor Briggs, Scott Adams and Don Surber (new book: Trump the Press) were on to Trump a year before anyone else was taking him seriously, not really because of stats, but just because they were listening to what Trump was saying and how the voters were reacting to him.
Always, the limits of error and polling sample size are never mentioned in all this.  Once you do that, you can see how absurdly small are the sample sizes (and where they come from) and large are the error bars.  Put those together and anyone can win.
Then, look at the size of the Trump rallies….the enthusiasm. I mean, haven’t these clowns watched Triumph of the Will?
It was a truly major disaster for the pollsters. Another one of many. They fell for the latest fad—in this case, Big Data.
Also, it’s not that she didn’t “get the message across” or anything like that.  The voters DIDN’T LIKE THE MESSAGE!  They got it all right. That’s why they voted for Trump.
Rebel Yell
He then added:

Of course their approach was wrong, but it was little to do with data.  Look, a chunk of the electorate is going to vote Republican, whatever, and a chunk Democrat, whatever.

If I’m a floating voter who may vote Clinton, or may vote Trump, you want my vote.  If you call me and my buddies ignorant, racist, xenophobic, prejudiced whatevers, because we’re thinking of voting for Trump, do you really think that I would consider voting for you?  Is that the approach that is going to attract voters? Big Data has nothing to do with it; it’s just common sense when you consider the attitude of the Democrat toady media and the progressive left.
The Clinton campaign, despite its obsession with hi-tech stuff, was the stupidest campaign I’ve seen in a long time.  And BTW, the Remainiacs in the UK did the same thing during the EU Referendum vote.  Look where that got them.
If you are running a candidate who is a lying, crooked, plastic robot who tries to do human imitations, at least try to make her seem human.  The overweening, oceanic sense of entitlement that oozed from her every pore was enough to make a maggot gag, but the campaign did everything to impress that on the voters.  Trump’s bloviating, brash approach was a big feature, not a bug, in his system.  He talked like ordinary people.  That’s how he got to them.  Scott Adams was on to this from day one.  And all his predictions turned out to be correct.  All of them.  No Big Data required.
The Duke of Toronto then bestirred himself from the sofa to write:
Well Ranted Rebel Yell
Stupid is a Stupid does…..they were sold a Bill of Goods for delivery of election results (based on using an untested process I should mention)  by some pencil necked geeks with higher maths and not much else. Occam’s razor applies in explaining the event  as your last mail underlines.
Arran Gold then found the piece of data that tells the important story. It appears that people who liked neither candidate voted for Trump by considerable margins.

The Hidden Group that Won the Election for Trump: Exit Poll Analysis from Edison Research

By: Larry Rosin “I don’t think there’s ever been two more unlikeable candidates,’ said Michael Che during the Weekend Update sketch on Saturday Night Live this week.  “Not one time in this election have I heard anyone say: ‘You know what? I like them both.’” The data from the Exit Polls conducted by Edison Research for the National Election Pool show Mr. Che to be correct – an extremely small portion of the voting public (only 2%) told our exit pollsters they had a favorable view of both.  While most voters did have a favorable view of one of the two major candidates – an astonishing 18% of the electorate told us they had an unfavorable opinion of both Hillary Clinton and Donald Trump.  And this is the group that won the election for Trump. …..

The story gets even more pronounced when we look at the states that swung the election to Trump.  In each of the cases in the table below, the votes gained by people who said: “I don’t like Trump but I’m going to vote for him anyhow” is greater than his total margin in these states.  In other words – it was the “Neithers” who pushed Trump over the top in these states and ultimately won him the election.

State % “Neithers” Trump Clinton
Wisconsin 22% 60% 23%
Pennsylvania 17% 56% 31%
Michigan 20% 50% 29%
Florida 14% 61% 24%
North Carolina 15% 63% 28%

The “Neithers” are more likely to be men (61%) and are more likely to be age 30-44 than in the younger or older age groups.  They are 78% white, as compared to the total electorate which is 70%. One of the most intriguing aspects of the “Neithers” is that a significant portion of those who were unfavorable to both Clinton and Trump were favorable to President Obama.  Nearly half of those who didn’t like either of this year’s two major candidates do have a favorable impression of President Obama – and a significant portion of this group voted for Trump. The 2016 election was unique in so many ways.  One distinguishing characteristic is just how many people had an unfavorable impression of both of the major party candidates.  To be sure, some of these people decided not to vote for either – Gary Johnson and Jill Stein combined for 18% of the vote among the “Neithers.”  However in the end, far more people who liked neither candidate chose Donald Trump and that provided him with his margin of victory in the battleground states.

The last mentioned article is both persuasive and relevant. It asked the right questions, and gets the right answers.  I particularly like the fact that many of the Trump votes liked Obama. The same nation elected them both.