This is a guest post from Roger Pielke, Jr., a professor of environmental studies at the University of Colorado at Boulder. Check out Pielke‘s blogs for more on the perils of predicting and “false positive science.”
Sports provide a powerful laboratory for social science research. In fact, they can often be a better place for research than real laboratories because sports provide a controlled setting in which people make frequent, real decisions, allowing for the collection of copious amounts of data. For instance, last summer, Daniel Hamermesh and colleagues used a database of more than 3.5 million pitches thrown in major league baseball games from 2004-2008 to identify biases in umpire, batter, and pitcher decision making. Similarly, Devin Pope and Maurice Schweitzer from the Wharton School used a dataset of 2.5 million putts by PGA golfers over five years to demonstrate loss aversion – golfers made more of the same-length putts when putting for par or worse than for birdie or better. Such studies tell us something about how we behave and make decisions in settings outside of sports as well. Read More »
Dan Johnson, an economist at Colorado College, has been predicting Olympic medal counts for years with a model that uses metrics like population count, income per capita, and home-country advantage. In the past six Olympics, his model has a correlation of 93 percent between predictions and actual medal counts, and 85 percent for gold medals.
For the Games in London this summer, Johnson predicts that the U.S. Will be the top medal winner, followed by China, Russia, then Britain — the same order they finished in the 2008 Beijing Olympics. Read More »
From Elizabeth Stanton at Bloomberg:
The New England Patriots will win the Super Bowl by at least three points even though the New York Giants have the appeal of “a cocktail party stock,” according to a quantitative money management firm that’s correctly picked the team covering the point spread for eight consecutive years.
Analytic Investors LLC in Los Angeles has documented a tendency on the part of Super Bowl bettors to overestimate the chances of the team that rewarded them more during the regular season — the team with the higher alpha, in investment parlance. In 2008, that was the favored Patriots, who lost to the Giants 17-14. This year, it’s New York.
“Everyone thinks the Giants are rolling right now, a lot of people in my office even,” said Matthew Robinson, a portfolio analyst for global and Japanese equities at Analytic and the author of this year’s analysis. “They like the Giants, but they have faith in the model as well.”
At least this is less ridiculous than the Super Bowl Indicator.
Our “Folly of Prediction” podcast included an interview with Joe Prusacki, who directs the statistics division at the USDA’s National Agricultural Statistics Service. This means he helps make crop forecasts (read a primer here). As hard as the USDA works, the fact is that predicting the future of even something as basic as crop yield can be maddeningly difficult. The Wall Street Journal has the latest in an article headlined “Erroneous Forecasts Roil Corn Market“:
Read More »
Government reports about the U.S. corn crop have become increasingly unreliable of late, contributing to wild swings in corn prices, a Wall Street Journal analysis shows.
Over the past two years, the Department of Agriculture’s monthly forecasts of how much farmers will harvest have been off the mark to a greater degree than any other two consecutive years in the last 15, according to a Journal analysis of government data. This year’s early-season forecasts also appear to have been way off. The next monthly report is due on Friday.
Contrary to popular perception, most research yields very few conclusions with 100 percent certainty. That’s why you’ll often hear economists state their conclusions with “95 percent certainty.” It means they’re pretty sure, but there’s still a small margin for error. The science of climate change is no different, and, according to a Washington Post blog post, scientists are currently struggling with how to explain that uncertainty to the public. “What do you do when there’s a small but real chance that global warming could lead to a catastrophe?” asks Brad Plumer. “How do you talk about that in a way that’s useful to policymakers?” Read More »
In conjunction with our latest Freakonomics Radio podcast, “The Folly of Prediction,” I decided to reach out to a former professor of mine, Raymond Horton, whose modern political economy class is a student favorite at Columbia Business School. I wanted to know what Horton thought the worst prediction ever was, particularly regarding the intersection of politics and economics. He immediately pointed to a Foreign Affairs essay written by Mortimer Zuckerman in 1998, in which Zuckerman boldly lays out the case that, like the 20th century, the 21st will also be marked by American dominance.
We’re barely a decade into the new century, so you may think it’s too early to pass judgment on Zuckerman’s prediction. But given the way things have played out over the last several years, it does look to be on shaky ground. At least that’s the opinion of Ray Horton.
Once you’ve finished reading Horton’s essay, we’d love to hear what you think count as some of the worst predictions ever. Read More »
In our latest podcast, “The Folly of Prediction,” we poke fun at the whole notion of forecasting. The basic gist is: whether it’s Romanian witches or Wall Street quant wizards, though we love to predict things — we’re generally terrible at it. (You can download/subscribe at iTunes, get the RSS feed, or read the transcript here.)
But there is one emerging tool that’s greatly enhancing our ability to predict: algorithms. Toward the end of the podcast, Dubner talks to Tim Westergren, a co-founder of Pandora Radio, about how the company’s algorithm is able to predict what kind of music people want to hear, by breaking songs down to their basic components. We’ve written a lot about algorithms, and the potential they have to vastly change our life through customization, and perhaps satisfy our demand for predictions with some robust results.
One of the first things that comes to mind when people hear the word forecasting is the weather. Over the last few decades, we’ve gotten much better at predicting the weather. But what if through algorithms, we could extend our range of accuracy, and say, predict the weather up to a year in advance? That’d be pretty cool, right? And probably worth a bit of money too.
That’s essentially what the folks at a small company called Weather Trends International are doing. The private firm based in Bethlehem, PA, uses technology first developed in the early 1990s, to project temperature, precipitation and snowfall trends up to a year ahead, all around the world, with more than 80% accuracy. Read More »
In our latest Freakonomics Radio podcast, “The Folly of Prediction,” we talk about the incentives behind making predictions, and how wrong predictions often go unpunished, which is why people make so many of them.
But recent news out of Italy seems to take the premise of punishing bad predictions a bit too far. From the New York Times:
Read More »
Seven Italian seismologists and scientists went on trial on manslaughter charges on Tuesday, accused of not adequately warning residents of a central Italian region before an earthquake that killed 309 people in April 2009. Prosecutors say that the seven defendants, members of a national panel that assesses major risks, played down the risk of a major earthquake’s occurring even though there had been significant seismic activity near L’Aquila, the capital of the Abruzzo region, in the months before the quake.