Durbin Watson Statistic

A test for first-order autocorrelation (correlation between successive values) in the residuals of a regression analysis. The Durbin-Watson statistic is approximately equal to 2 (1 - R), where R equals the correlation coefficient measuring the association between successive residuals. As the Durbin-Watson statistic approaches 2, it is more likely that the residuals are independent of each other, at least successively. With economic and financial data, it is often possible to reduce autocorrelation in the residuals by transforming the data into percentage changes.

Glossary * D