The Wall Street Journal, As of Thursday, October 9, 2003

Nobel Econometricians

By DAVID R. HENDERSON

The Nobel committee has announced its award of the Nobel Prize in economics to Robert F. Engle, an American at New York University, and to Britain's Clive J.W. Granger, an emeritus professor at the University of California, San Diego. Both are econometricians; that is, they specialize in the technical study of empirical relationships among various economic variables. The tools that econometricians develop are used by economists to understand a wide range of economic issues. Messrs. Granger and Engle's contributions sound, and, frankly, are, highly technical. Mr. Granger earned the award "for methods of analyzing economic time series with common trends (cointegration)." Mr. Engle earned his half "for methods of analyzing economic time series with time-varying volatility (ARCH)." These terms probably mean little to most readers. Yet their contributions profoundly affect many facts and ideas reported in The Wall Street Journal.

Start with Mr. Granger, who studied nonstationarity. A variable is nonstationary when it has no clear tendency to return to a constant value or trend. The consumer price index and the value of the euro in U.S. dollars are two such variables. Yet, into the 1980s, economists studying such variables, and knowing full well that they were nonstationary, still used models based explicitly on the assumption that the variables were stationary. In 1974, Mr. Granger and co-author Paul Newbold showed that using such models could yield statistically significant relationships between two sets of nonstationary data even when the data were generated randomly. A fix was needed. Mr. Granger provided the fix with his concept of cointegration, a concept too difficult to explain briefly. 

Economists have used cointegration to solve an important puzzle. The textbook view is that when your wealth increases by, say, $50,000, due to an increase in stock prices, then, if the real interest rate is, say, 5%, you would increase your annual consumption spending by 5% of $50K, or $2,500. But neither the stock-market crash of 1987 nor the boom of the 1990s caused as large a change in consumption as the textbook view predicted. How come? NYU economists Martin Lettau and Sydney Ludvigson give the answer in a recent paper published by the National Bureau of Economic Research. They show, using cointegration, that as much as 88% of the variation in household net worth since World War II is transitory. People, sensibly, don't spend much from wealth that they think won't last. At least not when it's their own.  

Robert Engle's work deals with the fact that the volatility of many variables varies over time. Large changes in stock-market returns, for example, are often followed by large changes, and small changes by small. To deal with this fact, in the early 1980s, Mr. Engle introduced -- are you ready? -- autoregressive conditional heteroskedasticity (ARCH). His ARCH model can be used to forecast volatility, something that is crucial for investors who want to limit the riskiness of their stock holdings. An Engle student, Tim Bollerslev, generalized his model, calling it, naturally, GARCH.  

GARCH has served a practical use in so-called value-at-risk analysis. Value-at-risk models are used to calculate capital requirements for compliance with the Basel rules that regulate risks in international banking. Using GARCH, economists can figure out how risky a portfolio can be while having only some specified small probability of a maximum loss. Individual investors can do likewise. In an example given on the Nobel committee's Web site, if you had $1 million in an S&P 500 index on July 31, 2002, your maximum loss the next day, with probability 0.99, was $61,500, or about 6%.  

Did this year's winners deserve the Nobel Prize? Given the importance of their work to the study of economics, the answer is yes. But the fact that the Nobel cannot be awarded posthumously, combined with the relative youth of the winners (Mr. Granger is 69 and Mr. Engle only 61), means, tragically, that some highly influential older economists are likely to be overlooked.  

Three main candidates come to mind: Armen Alchian , age 89, Gordon Tullock (81), and Arnold Harberger (79). Mr. Alchian , an emeritus professor at UCLA, laid out, in a path-breaking series of articles, how property rights affect economic behavior. He used his model to explain issues ranging from the effects of tenure to why regulated companies have traditionally discriminated against minorities. (Disclosure: Mr. Alchian was one of my mentors at UCLA.) Mr. Tullock, of George Mason University, co-founded, with Nobel laureate James Buchanan, the public-choice school, which uses economic analysis to understand the workings of government. Finally, Mr. Harberger, previously at the University of Chicago and now at UCLA, developed clever, yet amazingly simple, techniques to estimate the costs of various taxes and the loss in efficiency from monopoly. He also did much of the heavy analytic lifting that helped his so-called Chicago Boys turn around Chile's and other South American countries' economies. It would be nice if next year's Nobel committee gave some of these worthies a last hurrah.

Mr. Henderson, research fellow at the Hoover Institution and economics professor at the Naval Postgraduate School, is author of "The Joy of Freedom: An Economist's Odyssey" (Prentice Hall, 2001).