CEPR - Center for Economic and Policy Research

Multimedia

En Español

Em Português

Other Languages

Home Publications Blogs Beat the Press Michael Gerson Has Trouble with Numbers and Is Jealous of Those Who Don't

Michael Gerson Has Trouble with Numbers and Is Jealous of Those Who Don't

Print
Tuesday, 06 November 2012 05:37

Michael Gerson used his column today to make a bizarre attack on the NYT's polling analyst Nate Silver. He complains to readers:

"Silver’s prediction is not an innovation; it is trend taken to its absurd extreme. He is doing little more than weighting and aggregating state polls and combining them with various historical assumptions to project a future outcome to project a future outcome with exaggerated, attention-grabbing exactitude. His work is better summarized as an 86.3 percent confidence that the state polls are correct."

Actually Silver is doing nothing more than weighting and aggregating state polls and combining them with various historical assumptions. He is very clear on this. Gerson can go to Silver's website and find in great detail the methodology that Silver uses for weighting various polls based on their past track records. Gerson apparently thinks this is an indictment, complaining about Silver's precise 86.3 percent probability estimate.

The real problem here is simply that Gerson does not understand what Silver is doing. Silver's 86.3 percent prediction is premised on the assumption that the polls do not contain a systemic bias and that there is not some event(s) that radically shifts the attitude of the electorate between the last round of polls and the election. With these assumptions we can treat the polls as comparable to the draw of white and black marbles out of a huge jar.

If we take enough draws of 1000 balls (you're welcome to use a different number) and the average of each of these draws is that 50.5 percent of the marbles are black, we can begin to say with great confidence (which can be specified with many decimal points) that the majority of the marbles in this huge jar are in fact black. This is what Nate is doing. He does adjust the draws -- some polls consistently find more white or black marbles than the average of the other polls. Unless these polls have proved to be accurate in these divergences, Nate makes an adjustment for their tendency to find too many white or black balls. This process is the value-added that Nate provides over a simple averaging of the various polls.

This doesn't guarantee that Nate will prove right. There could be some systemic bias in the polls. This would be comparable to a situation where the black balls are heavier and therefore fall to the bottom and are less likely to be in the draw. The way to argue this case is to present a reason for why the polls could be biased. There are possible stories here: voters with only a cell phone may be undercounted, the assumptions about who is a likely voter may prove wrong, or the polls may be undercounting Spanish speaking voters.

These factors, and others, could lead to a systemic bias in the polls. But if Gerson, or anyone else, thinks this is the issue now, then it is incumbent on them to make the case, not get angry at Silver for using statistical methods.

The real problem is that Gerson just seems to have difficulty with numbers. He concludes his piece by telling readers:

"And so, at the election’s close, we talk of Silver’s statistical model and the likely turnout in Cuyahoga County, Ohio, and relatively little about poverty, social mobility or unsustainable debt."

Yes, it would be great if we had more discussion of poverty and social mobility throughout the campaign and beyond. It's hard to blame Silver for the lack of such discussion. The pre-Silver elections were not exactly dominated by serious discussions of major national issues. I recall in the 1988 presidential election when the big issues in the race between George H.W. Bush and Michael Dukakis were Willy Horton and the pledge of allegiance.

As far as the third item on Gerson's list, unsustainable debt, this is where his knowledge of math again fails him. Here is the ratio of interest payments to GDP over the last four decades:

interest-per-gdp-10-2012

Source: Congressional Budget Office.

As can be seen, the debt burden is very far from unsustainable, the interest burden is near its post-war low. In other words Gerson is angry because he thinks that somehow Silver's polling analysis has diverted the country from discussing a non-existent problem.

 

Comments (17)Add Comment
Election Fraud Worm Infects BTP Server
written by Robert Salzberg, November 06, 2012 6:27
The Justice Department is scrambling this morning after discovering a worm on the Beat The Press server that doubles sends all messages.

After further investigation, the Justice Department discovered that the computer virus picks just 1% of the messages and sends them twice. The virus has been tracked to computers in 6 swing states so far.

Panditas
written by David, November 06, 2012 7:10
The pundits are just mad that their BS color commentary on elections and economics is being made obsolete. The emperor has no clothes and they're mad about being exposed and about having to share their thunder. It will hit them in the pocketbook.
Knowledge of math is a terrible thing
written by Intro, November 06, 2012 7:31
The debt is described as "a non-existent problem: problem in this article. He uses a chart of interest as A % of GDP to prove his point, but this is a perfect example of misinformation.
Does anyone notice that total debt has quadrupled from 1992 to now, yet % debt to GDP has halved? Why is this? GDP has not grown by 800%. It is because interest rates on the debt are at historically low levels, at negative real interest rates. How many people think this is going to last? When this changes, and it will, then we will see why it is unsustainble.
If you look at the graph above, you see it correlates to interest rates, not GPD. If we return to interest rates of 1992, our % debt to GDP is 12%. If it returns to 1982 levels, it goes to 24%! And that is at todays debt levels, which are only expected to increase.
If we look at interest on debt under the current CBO budget projection, at todays interest rates, in 4 years the interest payment exceeds defense spending. In 4 years, if interest returns to 1982 levels, interest as % of GDP will be just under 50%.
I would call debt interest under current rates unusustainable at todays rates. Debt interest at historical rates will make the "Great Depression" a "bump in the road" to steal Obamas rhetoric.
And the author calls this a non-existent problem?
Shorter Gerson
written by Matt, November 06, 2012 7:56
Shorter Gerson: "F**king mathematics, how does it work?"
Will Is Always Right
written by bobs, November 06, 2012 7:57
The infallible George Will is predicting a landslide for Romney.

George Will predicted the election of Abraham Lincoln back when he was a young journalist. The man knows.
...
written by JDM, November 06, 2012 8:37
Yes, Intro, if something happened which is incredibly unlikely to happen, things could be worse. Your scenarios would require no change whatsoever in the present debt amount and interest rates to skyrocket for no particular reason at all (the market says it's not going to happen). That is a non-existent problem; it's pretty much the definition of a non-existent problem.
...
written by David, November 06, 2012 8:39
I think we are not looking at the bright side of having the opportunity of being in competition for market share with Luddites. Perhaps we should stop pulling their handwoven coats and rather praise them for their fealty to their traditions.
...
written by Clifton, November 06, 2012 10:02
Silver's 86.3 percent prediction is premised on the assumption that the polls do not contain a systemic bias and that there is not some event(s) that radically shifts the attitude of the electorate between the last round of polls and the election.


Actually I don't think Silver assumes that there is no systemic bias in the polls. If one makes this assumption, the probability of an Obama victory would be much higher. Instead he looks at past polling to determine the percentage of time there is a systemic bias, and the size of these biases. Then he adjusts Obama's chance of victory down accordingly. Nor does he assume that there will be no event that radically shifts the voters attitudes before the election. This is one of the reasons that the "now-cast" was different from the the forecast.
...
written by liberal, November 06, 2012 11:01
Intro wrote,
It is because interest rates on the debt are at historically low levels, at negative real interest rates. How many people think this is going to last?


But if rates go back up again due to a strengthening economy, the deficit will have shrunk anyways, as revenues start to rebound.
Waste on health care dwarfs interest on the national debt
written by Rachel, November 06, 2012 12:46

Roughly $800 billion is what we overspend each year on doctors, nurses, hospitals, pharmaceuticals, etc. (That's taking McKinsey's 2006 figure, $650, and multiplying it by 123 percent, which is how much medical spending has grown in just six years.)

But who discusses this big chunck of a trillion dollars wasted each year? And it would not be necessary to have a Single Payer to lower some of the administrative costs. But this option is almost never mentioned.

And if medical overspending is not worth talking about, why bother with the half trillion spent on interest?


math
written by jennifer reft, November 06, 2012 1:59
The backlash against Nate Silver has been amazing. As you describe, he has method to his predictions that is not very novel or terribly unique, and if you read his blog he is always explaining it. There are many places you could disagree with him on, but it is noteworthy that his critics are NOT doing that. Instead they are literally calling him names. You have to wonder if people cannot understand simple probabilites and statistics, how are they going to understand budgets or global warming.
...
written by Bart, November 06, 2012 4:12

As Brad DeLong often laments, "Why can't we have a better press corps?"
Math is hard work !
written by H-Bob, November 06, 2012 6:13
The GWB administration's budget said that the Bush tax cuts would pay off the national debt as fast as the Treaury bonds matured !
...
written by skeptonomist, November 07, 2012 6:20
The number after the decimal point in 86.3 is certainly superfluous - giving the probability to the nearest 10% would be more reasonable. So there is some merit in Gerson's first paragraph - the rest is foolishness.
...
written by liberal, November 07, 2012 7:08
skeptonomist wrote,
... giving the probability to the nearest 10% would be more reasonable.


I think that's exactly what Andrew Gelman suggested.
Conflating deficit reduction and spending cuts
written by Nick Batzdorf, November 07, 2012 2:22
http://www.washingtonpost.com/...story.html

Curious that the headline says Fitch is warning that Obama must strike a deal to reduce the deficit, while the article says the warning is against the tax increases and spending cuts.
US debt to gdp has not halved since 1992
written by Emersberger, November 09, 2012 12:32
INTRO wrote

“Does anyone notice that total debt has quadrupled from 1992 to now, yet % debt to GDP has halved? Why is this? GDP has not grown by 800%.”

Debt to GDP ratio has not halved!

You can easily go to tradingeconomics dot com and verify this for yourself.

In 1992 the USA’s gross public debt to gdp ratio was 64.1%. As of 2011, it was 103%

In 1992 the USA’s nominal GDp has grown from roughly 6 to 15 trillion between 1992 and 2012. In other words nominal GDP is about 2.5 times larger in 2012 than in 1992.
That mean nominal public debt in the USA grew by about 4.2 times over that period as you say – which seems to be the only thing you got right in your post.

PLEASE NOTE. All the numbers above are for gross debt. Net debt – which accounts for what the the government owes as well as what it owns is presently at about 82% of gdp. You can verify this at the same website.

Dean has presented 4 DECADES worth of data, which includes periods of very high real interest rates. As someone noted above, it makes no sense to fear strong economic growth will make public debts unsustainable. Exactly the opposite is what people should fear.

Write comment

(Only one link allowed per comment)

This content has been locked. You can no longer post any comments.

busy
 

CEPR.net
Support this blog, donate
Combined Federal Campaign #79613

About Beat the Press

Dean Baker is co-director of the Center for Economic and Policy Research in Washington, D.C. He is the author of several books, his latest being The End of Loser Liberalism: Making Markets Progressive. Read more about Dean.

Archives