Forecasting the weekly time-varying beta of UK firms:comparison between GARCH models vs Kalman filtermethod

摘要

This paper investigates the forecasting ability of four different GARCH models and the Kalman filtermethod. The four GARCH models applied are the bivariate GARCH, BEKK GARCH, GARCH-GJRand the GARCH-X model. The paper also compares the forecasting ability of the non-GARCH modelthe Kalman method. Forecast errors based on twenty UK company weekly stock return (based on timevarybeta) forecasts are employed to evaluate out-of-sample forecasting ability of both GARCH modelsand Kalman method. Measures of forecast errors overwhelmingly support the Kalman filter approach.Among the GARCH models both GJR and GARCH-X models appear to provide somewhat moreaccurate forecasts than the bivariate GARCH model.