# blueollie

## Poll watchers: don’t let “convention bounces” fool you…

For those unfamiliar, a support for a presidential candidate appears to go up right after the convention for that party. For example, you can see that Trump’s support appeared to go up after the Republican Convention. Now you can see a similar uptick in Hillary Clinton’s support now that the Democratic convention is over.

from here

That uptick is called a “convention bounce”. Political scientists have wondered why this occurs. Here is the reason: a polling outfit gets its data by making random calls. Of course, only a certain percentage of voters take the calls and only a certain percentage of voters are willing to be polled.

It turns out that right after a party’s convention, a higher than normal percentage of people who support that party’s candidate are willing to be polled! In other words, right after the Republican Convention, the sample had a higher than normal percentage of Trump supporters whereas, right now, a higher than normal percentage of Clinton supporters are answering the pollster’s questions.

This is called “sample bias”.

Upshot: we really won’t have an accurate read of the election until a couple of weeks from now.

August 2, 2016

## Trump Speech: fantasy

Workout notes: yesterday, 2 extra walking miles (to check out my smart phone map feature) and to see what my “just walking” pace is like. It is about 17 minutes per mile. Then 5K more this morning (15-ish mpm) after lifting weights.

lifting: rotator cuff, pull ups: 5 sets of 10
squats: 2 weightless sets of 10, 10 x 45, then 4 sets of 5 goblet squats: 25, 35, 50, 50
The “tug” in my right inner leg was barely noticeable, at times.

bench press: 10 x 135, 4 x 185, 10 x 170 incline press: 10 x 135
military: dumbbells, 7 x 50 standing (sloppy), 15 x 50 seated, supported, 10 x 40 standing.
rows: 3 sets of 10 x 50 (dumbbell) each arm
abs: 2 sets of 12 twist crunch 10 yoga leg lifts

Trump’s Speech and the election.
In a nutshell, you need to be SCARED and to understand that Trump is the ONLY ONE who can fix it.

Yes, better infrastructure (which I do want), less crime, a quick win of the war against ISIS and other terrorist organization, all the while cutting taxes and building that huge wall between US and Mexico. He is going to do ALL of that, VERY QUICKLY (though it took him 73 minutes to tell us that). How? Just trust him; just believe.

Red State Update gave more or less the same speech in 2008, but in a much briefer period of time:

Oh by the way, the world is NOT falling apart, crime is actually down overall (though up in some locations); you can read the rest of the fact checks here.

As far as how the race is going: this is a great resource. Upshot has its own model, and it links to many other models and betting markets. The map hasn’t changed much from the 2012 map.

You’ll read a lot about “Hillary’s support is sinking”. The reality is that “no incumbent in the race” elections tend to be close. As I told a friend:

In my lifetime, there have been 5 “no incumbent” elections. The popular vote margins (in percent) have been:
0.17 (1960 Kennedy vs. Nixon)
0.7 (1968 Nixon vs. Humphrey)
7.72 (1988 Bush I vs. Dukakis )
-0.51 (2000 Bush II vs. Gore, Gore won the popular vote)
7.27 (2008 Obama vs. McCain)
So if there is a poll or two that shows Hillary with a double digit lead…it is probably an outlier. So don’t be surprised to read “Hillary sinking in the polls”; that usually means that there was a favorable outlier followed by a more realistic result. Expect, for statistical reasons, to see a few polls here and there that show Trump leading. A typical margin of error is 3 to 4 points and that is the MOE for the SUPPORT of a candidate, not for the difference. Example (two way example) if she really leads 52-48, Hillary’s support in a single given poll will vary between 48 to 56 percent 95 percent of the time, so one can expect to see her trailing by 4 points in some polls and winning by 12 in others.

July 22, 2016

## About those general election polls…

Yes, there has been some tightening in the polls. I’ve seen a few maps; 538 shows:

The betting lines show slightly lessened odds for Sec. Clinton:

Clinton was at 4/11 and now she is at 2/5 (the larger the fraction, the worse the odds).

Nate Silver gives a lengthy explanation of why the recent batch of polling changed the model a bit. But while Clinton’s support took a bit of a hit, Trump’s support really didn’t get a bump up.

And so, with the caveats that past Presidential elections are small in number, I’ll just say this: here are the elections in my lifetime. I voted in the last 9 of these. I’ve listed the percentage difference (popular vote) between the winner and the loser:

 year difference 1960 0.17 1964 22.58 1968 0.7 1972 23.15 1976 2.06 1980 9.74 1984 18.21 1988 7.72 1992 5.56 1996 8.51 2000 -0.51 2004 2.46 2008 7.27 2012 3.86

Three elections were decided by LESS than 1 percent of the vote, 3 between 1 and 5 percent, 5 between 5-10 percent, and 3 were 10 percent or more (landslides)

But if you look at the “no incumbent in the race” elections, the differences were 0.17, 0.7, 7.72, -0.51 and 7.27 percent.

That is, modern Presidential elections tend to be close, especially when no incumbent is in the race. And so, if the polls really are random, you would not expect one candidate to consistently poll higher than the other. In fact, the margin of error for the support of a given candidate is typically 3-4 points, which translates to a 6-8 percent margin in a two way poll. So even if Hillary Clinton is “really” head by 7 points nationally, you’d expect to see a few polls showing Trump to be slightly ahead. If her lead was really, say, 3 points, you’d expect to see a few polls showing Trump in the lead.

So, while this election is competitive (for now), expect to see a few polls showing Trump head.

July 14, 2016

## Rant: recognizing the limits of what one knows

I’ll admit that I am an expert in a very narrow slice of mathematics. But I am at least an AU from being an international or even a national caliber expert in that narrow field of mathematics.
And yes, I often read about topics that are not in my area; I enjoy popular books and articles on topics from the various branches of science, economics and the like.

Nevertheless, I also realize that when I read such a book or article, or when I attend a public lecture, I am getting a watered down, simplified treatment of the subject. I lack the context and the prerequisite knowledge to appreciate a presentation aimed at the experts.

And there lies one of my biggest frustrations when it comes to talking to people, either on the internet or in person. There are so many who really can’t detect the difference between expert knowledge and what they read (and perhaps half-digested …if that much) from a popular book. It is THAT level of “lack of humility” that makes some unpleasant conversation companions; I am ok with ignorance. After all, I am ignorant of the vast majority of human knowledge. I think that all of us are.

And, sadly, I see this lack of intellectual humility in political or social issues discussion, especially from the “losing side”. It appears to me that being on the losing side of an election (and I’ve been there, many, many times) brings out the worst in people in several ways.

Example: I had someone try to tell me that Hillary Clinton’s popular vote is “within the margin of error”, when one factors in the caucus states.

Of course, that is a dumb statement for a number of reasons.

1. There is a difference between a vote count and a poll count, even though both have a margin of error (remember Florida in the 2000 general election). The margin of errors in vote count is much smaller than it is for a poll.

2. The margin of error for a poll is $1.96 * \frac{.5}{\sqrt{n}}$ (assuming a 95 percent confidence interval and a relatively close election; this comes from the normal approximation to the proportion distribution. So as $n$ increases, the confidence interval, and therefore the margin of error, decreases. Note: for more on polls, read this wonderful little article written by a physics professor.

3. Hillary Clinton leads by about 3 million votes, even when one counts the caucus votes. The latter doesn’t add much as there are fewer caucus states, and these tend to be smaller states. Anyhow, she leads about 57-43.

4. The person making the claim appeared to not understand that winning a small state by a very large percentage didn’t make up for winning a bigger state by a smaller margin.

Yes, by knowing that Sanders won a lot of caucus states and that there IS such a thing as margin of error puts this individual into the “above average” category. But this person was clearly ignorant of their own ignorance.

There is another factor in play: I really think that desperation makes one dumber. When one really likes a candidate or a person, or even a sports team, it is tough to accept an unpleasant reality. I’ve become acquainted with the latter as an Illinois football fan (“yeah, we have a shot at being Wisconsin!” Sure.)

Desperation can lead to an abandonment of one’s values. Check out the Republican Chairman’s take on Donald Trump

Oh sure, few would be surprised at Donald Trump’s behavior, and I doubt that a certain type of Republican really cares that much (“hey, what do you expect with Trump anyway?”)

May 16, 2016

May 4, 2016

## Political Spin 101.

Get a load of the e-mail that the Sanders campaign sent out (I am on the list as I bought a Sanders shirt for my daughter)

Yes, ONE of the 10 recent polls shows only a 6 point gap. The other 9 polls, some of which are later…well…those aren’t such good news.

THIS is why the ardent supporters of a candidate feel cheated when the actual results come out.

April 17, 2016

## President’s Day Poll: Have some fun!

Ok, here is a list of the Presidents of the United States. Just for the fun of it:

1. List YOUR top three favorite Presidents that YOU can personally remember (in your lifetime, after you became aware)

2. List YOUR top three favorite Presidents that were BEFORE your time.

4. Vote in my poll (post WWII) for your favorite President.

5. IF you lean Democrat or Republican, who is your favorite President from “the other party”: all time AND “recently” (last, say, 30 years)

My picks:
1. Barack Obama, Bill Clinton, Jimmy Carter (that order)
2. Abraham Lincoln, F. D. Roosevelt, Harry Truman (I almost put Teddy Roosevelt here)
3. George W. Bush, Richard Nixon, Ronald Reagan (I am the only person in the USA who put Reagan on this list)
4. Barack Obama
5. Favorite Republican is Abraham Lincoln (liked Eisenhower and T. Roosevelt as well); favorite modern Republican was George H. W. Bush.

February 18, 2013

## Election Wrap Up III: my demographics

Data from CNN
I’ll see how “typical” I am:

Geography
Illinois: 57-41 Obama.
Peoria (County): 51-47 Obama.
Peoria (City of): 56-42 Obama.

Personal
Males: 52-45 Romney
Age 50-64: 52-47 Romney
Latino: 71-27 Obama
Age/Latino: 68-31 Obama
Non-religious: 70-26 Obama
Married: 56-42 Romney
Married men: 60-38 Romney

Politics/Issues
Decided my vote early: 53-46 Obama
Raise Taxes on 250K and up: 70-29 Obama
Health care: should be expanded: 92-5 Obama
Repeal Obamacare: no: 87-11 Obama

So you can see that my demographics (Illinois, City of Peoria, Race, Education, non-religious) really pointed me toward Obama. But by far, it was the issues (duh).

November 9, 2012

## Election Wrap Up II: a few stats from the General Election

First, a fun fact: (Via CNN Exit Polls)
About 7 percent of those voting for Barack Obama and 8 percent voting for Mitt Romney split their vote for the US House (e. g., 7 percent of Obama voters voted for a Republican for the US House, and 8 percent of Romney voters voted for a Democrat). I know quite a bit of that happened in IL-17, as Bustos won by 6 and Obama was up by about 15 points in that district.

I’ve decided to look at some national statistics from the previous 4 elections:

 year %voting R-total D-total EV-R EV-D 2000 50.4 50.4M, 47.9% 51.0M, 48.4% 271 266 2004 56.2 62M, 50.7% 59M, 48.3% 286 251 2008 61.6 59.9M, 45.7% 69.5M, 52.9% 173 365 2012 54.7 58.1M, 48% 61.1M, 50% 206 332

Note: after the 2004 election, President Bush was listed at 59 million votes; the number grew to 62 million as more votes were tabulated. Hence I anticipate that President Obama’s eventual totals will reach this number. And of course, as of the time of this writing, Florida has not been called; however the Romney campaign admitted that he is down by 58K votes and the remaining votes are from Democratic leaning areas.
Also, Obama’s vote total is projected to reach 66 million.

Fun Fact In 5 of the last 6 Presidential elections, the Democrat has won the popular vote. That feels strange to me because the first election that I followed was Nixon-Humphrey; that saw the Republicans win (and sometimes win BIG) 5 of 6 elections (popular and electoral); so it is my knee-jerk response to view the Presidency as something a Republican holds. The fact is, during my lifetime, Democrats have won 7 elections (8 times the popular vote), and the Republicans have won 7 elections (6 times winning the popular vote). It doesn’t get more even than that.

But my “set in stone” gloominess comes from my 4-5 record: I had losses with Carter, Mondale and Dukakis, and then with Gore and Kerry. Clinton and Obama gave me my 4 wins. I lost in my first 3 presidential elections. Obama was the sweetest win; Kerry was my most bitter loss, though I felt pretty alone when Reagan won his second term and I was stuck on a Navy base.🙂

My state and county

Obama won Illinois 57-41 with a margin of 2.91 million to 2.09 million. The biggest margin came in Cook County (Chicago); Peoria is part of the blue counties on the western border moving inward. There is a blue splotch in East Saint Louis; the one toward the East (by itself) is Champaign county (where the University of Illinois is). Obama won Peoria 51-47 (40 K to 36.6 K).

Some history:
The 2000 Election (red and blue are swapped from their traditional roles)

The 2004 Election

The 2008 Election

The unusual “red is Democrat, blue is Republican” maps are from US Election Atlas. The traditional maps are from CNN.

Data for Peoria County (city and countryside):
2000 Gore over Bush 50.2-47.4 percent, 38.6-36.4 (thousands)
2004 Kerry “over” Bush 49.7-49.6 percent, 41,121 to 41,051 votes (70 vote margin!)
2008 Obama over McCain 56-42 percent, 45.9-34.6 thousand
2012 Obama over Romney 51-47 percent, 40-36.6 thousand

Note: the population of Peoria County is 183.4 K, and rose 1.7 percent from 2000 to 2010. Hence the “best” turnout was for the 2004 election! Note also that traditionally the Democrat wins the City of Peoria whereas the Republican wins (except for 2008) the county minus the city.

Texas

2000 Election

2004 Election

2008 Election

2012 Election

As far as my old country (Travis county, home of the University of Texas)

2000: Bush won 46.9 to 41.7 percent
2004: Kerry won 56-42 percent
2008: Obama won 64-35 percent (254K to 137 K votes)
2012: Obama won 60-36 percent (231.5 to 139.5 K votes)

Note that in the last two elections, Obama won Austin, Houston, Dallas, San Antonio and El Paso; he lost Fort Worth. The blue stuff in the south part of the state (almost every year) is the heavily Hispanic rural area, and of course, El Paso.

My guess is that Jill Stein did well in Austin in 2012, especially given that Texas was a lock for Mr. Romney.

November 9, 2012

## The Real Winner Tonight…..

Well, of course I am happy that President Obama won tonight.

I am happy that Dave Koehler won: (IL-46 State Senate)

I am happy that Cheri Bustos won (IL-17 US House)

One is the battle of the nerds versus the traditional pundits. The outpouring of Hate for Nate has been awesome to watch; much of it is coming from the right, but a fair bit also from mainstream pundits who rely on their ineffable sense of “momentum” or whatever rather than polls.

Obviously I side, professionally and temperamentally, with the nerds here — not just Nate Silver, but Sam Wang, Drew Linzer, Pollster, and more. I’d like to think I’d be on their side even if the numbers were pointing the other way.

The point is that relying on data rather than hunches is my style; I’d hate, professionally, to see the voices in the air people get this right, simply because the polls were wrong.

First of all, from what I can see a lot of people have trouble with the distinction between probabilities and vote margins. They think that when I say, “state level polls overwhelmingly suggest an Obama victory”, I’m also saying “state level polls suggest an overwhelming Obama victory”, which isn’t at all the same thing. We have a lot of polls, almost all of which say that Obama will win Ohio; but they don’t by any means say that he’ll win it in a landslide.

Second, people clearly have a problem with randomness — with the fact that any poll, no matter how carefully conducted, has a margin of error. (And the true margins of error are surely larger than the statistical measure always reported, since sampling error isn’t the only way a poll can go wrong). Specifically, what I think people don’t get is the fact that when there are many polls of a state, some of them are bound to be outliers — not, or not necessarily, because the pollsters have done a bad job, but because there’s always noise in any sampling procedure.

What this means is that if you look at all the polls, you’re very likely to find one or two that tell you what you want to hear: Rasmussen has Ohio tied! Susquehanna has Pennsylvania tied! And it’s very tempting to select those polls and trumpet them — a temptation you really want to resist. The point isn’t necessarily that these are bad polling firms (as it happens, they are, but that’s beside the point); it is that even good pollsters will produce an occasional off result, and you really, really don’t want to start picking and choosing those off results to make yourself feel good.

So in a many-poll world, you really have to adopt some kind of averaging procedure and stick to it. Different poll aggregators have chosen slightly different methods, and it would be worrisome if they were telling different stories. But they aren’t: they’re all saying Obama advantage[…]

But people seem to have a trouble with math IF it goes against what they want to be true, or what “their gut” says is true.

November 7, 2012