Anatolyev, Stanislav and Gospodinov, Nikolay (2010) "Modeling financial return dynamics via decomposition", Journal of Business and Economic Statistics, Vol. 28, No. 2, pp. 232–245
While the predictability of excess stock returns is detected by traditional predictive regressions as statistically small, the direction-of-change and volatility of returns exhibit a substantially larger degree of dependence over time. We capitalize on this observation and decompose the returns into a product of sign and absolute value components whose joint distribution is obtained by combining a multiplicative error model for absolute values, a dynamic binary choice model for signs, and a copula for their interaction. Our decomposition model is able to incorporate important nonlinearities in excess return dynamics that cannot be captured in the standard predictive regression setup. The empirical analysis of US stock return data shows statistically and economically significant forecasting gains of the decomposition model over the conventional predictive regression.
Link to paper online:
Paper in accepted version:
Data used in the paper:
2008 North American Winter Meeting of Econometric Society, New Orleans, Louisiana, USA, January 4-6, 2008
Time Series Econometrics Seminar, Helsinki Center of Economic Research, Helsinki, Finland, March 26, 2007
XXII New Economic School research conference, Moscow, Russia, November 8-10, 2007
27th International Symposium on Forecasting, New York, USA, 2007 (by Nikolay Gospodinov)
13th International Conference on Computing in Economics and Finance, Montreal, Quebec, Canada, June 14-16, 2007 (by Nikolay Gospodinov)
Nyberg, H. (2011) "Forecasting the direction of the US stock market with dynamic binary probit models", International Journal of Forecasting, Vol. 27, pp. 561-578.
Thomakos, D.D. and Wang, T. (2010) "'Optimal' probabilistic and directional predictions of financial returns", Journal of Empirical Finance, Vol. 17, pp. 102-119.