One blogger’s personal bridge to nowhere

Dewey defeats Truman…no, I change my mind

In introductory Statistics class — one of the few I actually attended, apparently — I, along with my classmates, was taught the quintessential example of polling inaccuracy: the “Dewey defeats Truman” debacle in 1948.  The reason that that pre-election poll failed so abominably, we learned, was that pollsters had conducted their research by telephone — a still relatively expensive device at the time, one that was owned more by wealthier Republicans than by less well-off Democrats.  As a result, the figures for the Republican nominee, Dewey, were overstated, and significant areas of support for Harry Truman were undercounted.  Poll done badly, election turns out right.

This seemed quite simple, at the time.  It still seems quite simple.  And if I learned it in introductory Statistics class, I imagined that professional pollsters had learned it as well.  My mistake.

Of course, the balance of opinion could change, as it has several times in this campaign, and as it has in the past. Harry Truman was trailing Thomas E. Dewey by 5% in the last Gallup poll in 1948, conducted between Oct. 15 and 25 — the same margin by which Mr. Obama seems to be leading now. But on Nov. 2, 18 days after Gallup’s first interviews and eight days after its last, Truman ended up winning 50% to 45%. Gallup may well have gotten it right when in the field; opinion could just have changed.

This was Michael Barone, an AEI hack and former vice president of a polling form, in an entirely unnecessary Wall Street Journal op-ed.  After asking a provocatively leading question — “Can we trust the poll when one of the presidential candidates is black?” — Barone answers meekly, “yes — with qualifications,” and proceeds to cite those who have already published better takedowns of the “Bradley Effect.”  To fluff his piece, apparently, though, he feels the need to recite some irrelevant polling history.  Hence the Dewey-Truman anecdote.

Why get this example so bafflingly wrong, though?  I can only speculate.  Barone may just be a phenomenally bad pollster, but it seems more likely that this history simply reads better with the agenda he is trying to push.  If “opinion could just have changed” in that monumental polling disaster, then perhaps, in 13 days, “the balance of opinion could change,” and the millions of Americans who have rejected George Bush will change their minds on change, and realize that John McCain is the answer.

October 22, 2008 - Posted by | History, U.S. politics

1 Comment »

  1. I have heard several references to a problem with polling this cycle–that problem being that there are a lot of people who have only cell phones, and they do not get polled. This demographic (which includes myself, my wife, and a number of my contemporaries and firends) is younger and goes overwhelmingly for Obama. While those people are less likely to vote, I’d wager that a significant portion of them will. The exclusion of this modern demographic actually tilts polls in McCain’s favor.

    That being said, polls are just polls, and I never take anything before the election as incontrovertible evidence. Just effing vote for Obama, and don’t worry about what a plumber in Ohio does.

    Comment by Kenny B. | October 24, 2008 | Reply

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: