Nobel Prize in Economic Sciences
The Royal Swedish Academy of Sciences has decided that the
Bank of Sweden Prize in Economic Sciences in Memory of Alfred
Nobel, 2003, is to be shared between
Robert F. Engle
New York University, USA
“for methods of analyzing economic time series with
timevarying volatility (ARCH)”
and
Clive W. J. Granger
University of California at San Diego, USA
“for methods of analyzing economic time series with
common trends (cointegration)”
Statistical Methods for Economic Time Series
Researchers use data in the form of time series, i.e., chronological
sequences of observations, when estimating relationships and
testing hypotheses from economic theory. Such time series
show the development of GDP, prices, interest rates, stock
prices, etc. During the 1980s, this year’s Laureates
devised new statistical methods for dealing with two key properties
of many economic time series: timevarying volatility and
nonstationarity.
On financial markets, random fluctuations over time –
volatility – are particularly significant because the
value of shares, options and other financial instruments depends
on their risk. Fluctuations can vary considerably over time;
turbulent periods with large fluctuations are followed by
calmer periods with small fluctuations. Despite such timevarying
volatility, in want of a better alternative, researchers used
to work with statistical methods that presuppose constant
volatility. Robert Engle’s discovery was therefore a
major breakthrough. He found that the concept of autoregressive
conditional heteroskedasticity (ARCH) accurately captures
the properties of many time series and developed methods for
statistical modeling of timevarying volatility. His ARCH
models have become indispensable tools not only for researchers,
but also for analysts on financial markets, who use them in
asset pricing and in evaluating portfolio risk.
Most macroeconomic time series follow a stochastic trend,
so that a temporary disturbance in, say, GDP has a longlasting
effect. These time series are called nonstationary; they differ
from stationary series which do not grow over time, but fluctuate
around a given value. Clive Granger demonstrated that the
statistical methods used for stationary time series could
yield wholly misleading results when applied to the analysis
of nonstationary data. His significant discovery was that
specific combinations of nonstationary time series may exhibit
stationarity, thereby allowing for correct statistical inference.
Granger called this phenomenon cointegration. He developed
methods that have become invaluable in systems where shortrun
dynamics are affected by large random disturbances and longrun
dynamics are restricted by economic equilibrium relationships.
Examples include the relations between wealth and consumption,
exchange rates and price levels, and short and longterm interest
rates.
Robert F. Engle, born in 1942 (60 years), in Syracuse, NY,
USA (American citizen); Ph.D. from Cornell University in 1969;
Michael Armellino Professor of Management of Financial Services
at New York University, NY, USA.
Clive W. J. Granger, born 1934 (69 years), in Swansea, Wales
(British citizen); Ph.D. from University of Nottingham in
1959; emeritus Professor of Economics at University of California
at San Diego, USA.
