Stochastic Parameter Regression Models (Quantitative Applications in the Social Sciences)

Whereas standard regression models force economic relationships or behavior to be fixed through time, stochastic parameter regression models allow relationships to vary slowly--without need for specification of the causes of that variation. The authors thoroughly examine the usefulness of the Kalman filter and state-space modeling in work with the stochastic parameter regression model.

Paul Newbold was born in England in 1945. In 1966 he obtained a BSc in Economics at the London School of Economics, before continuing to study for a PhD in Statistics at the University of Wisconsin. He worked under the supervision of George Box, and was awarded his PhD in 1970. His first academic posts were at the University of Nottingham, where he spent time in both the Department of Economics and the Department of Mathematics. From 1979-1994 he was Professor at the University of Illinois, before returning to the University of Nottingham in 1994 as Professor of Econometrics. Paul Newbold has had a large influence on the discipline of time series econometrics, particularly in the areas of non-stationary time series, forecasting, and univariate time series analysis. He has published extensively in journals such as Journal of Econometrics, Journal of Business and Economic Statistics, Journal of the American Statistical Association, Biometrika, and Econometric Theory. He retired in 2006 and is now Emeritus Professor of Econometrics.