×

Optimal forecast combinations under general loss functions and forecast error distributions. (English) Zbl 1282.91266

Summary: Existing results on the properties and performance of forecast combinations have been derived in the context of mean squared error loss. Under this loss function empirical studies have generally found that equally-weighted combined forecasts lead to better performance than estimates of optimal forecast combination weights which in turn outperform the best individual predictions. We show that this and other results can be overturned when asymmetries are introduced in the loss function and the forecast error distribution is skewed. We characterize the optimal combination weights for the most commonly used alternatives to mean squared error loss and demonstrate how the degree of asymmetry in the loss function and skews in the underlying forecast error distribution can significantly change the optimal combination weights. We also propose estimation methods and investigate their small sample properties in simulations and in an inflation forecasting exercise.

MSC:

91B84 Economic time series analysis
62M10 Time series, auto-correlation, regression, etc. in statistics (GARCH)
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Bates, J. M.; Granger, C. W.J., The combination of forecasts, Operations Research Quarterly, 20, 451-468 (1969)
[2] Buchinsky, M., 1992, Methodological issues in quantile regression. Manuscript, Brown University.; Buchinsky, M., 1992, Methodological issues in quantile regression. Manuscript, Brown University.
[3] Chamberlain, G., A characterization of the distributions that imply mean-variance utility functions, Journal of Economic Theory, 29, 185-201 (1993) · Zbl 0495.90009
[4] Chan, Y.L., Stock, J., Watson, M.W., 1999. A dynamic factor model framework for forecast combination. Spanish Economic Review 1, 91-121.; Chan, Y.L., Stock, J., Watson, M.W., 1999. A dynamic factor model framework for forecast combination. Spanish Economic Review 1, 91-121.
[5] Christoffersen, P.; Diebold, F. X., Optimal prediction under asymmetrical loss, Econometric Theory, 13, 806-817 (1997)
[6] Clemen, R. T., Combining forecastsa review and annotated bibliography, International Journal of Forecasting, 5, 559-581 (1989)
[7] Diebold, F. X., Serial correlation and the combination of forecasts, Journal of Business and Economic Statistics, 6, 105-111 (1988)
[8] Diebold, F.X., 2001. Elements of Forecasting. 2nd Edition. South-Western Publishing.; Diebold, F.X., 2001. Elements of Forecasting. 2nd Edition. South-Western Publishing.
[9] Diebold, F.X., Lopez, J.A., 1996. Forecast evaluation and combination. In: Maddala, G.S., Rao, C.R. (Eds.), Handbook of Statistics 14. Elsevier, Amsterdam, pp. 241-268.; Diebold, F.X., Lopez, J.A., 1996. Forecast evaluation and combination. In: Maddala, G.S., Rao, C.R. (Eds.), Handbook of Statistics 14. Elsevier, Amsterdam, pp. 241-268.
[10] Diebold, F. X.; Mariano, R., Comparing predictive accuracy, Journal of Business and Economic Statistics, 13, 253-265 (1995)
[11] Diebold, F. X.; Gunther, T. A.; Tay, A. S., Evaluating density forecasts with applications to financial risk management, International Economic Review, 39, 863-883 (1998)
[12] Elliott, G., Timmermann, A., 2002. Optimal forecast combination weights under regime switching. Manuscript, University of California, San Diego.; Elliott, G., Timmermann, A., 2002. Optimal forecast combination weights under regime switching. Manuscript, University of California, San Diego.
[13] Fildes, R., Ord, K., 2001. Forecasting competitions: their role in improving forecasting practice and research. In: Clements, M.P., Hendry, D.F. (Eds.), A Companion to Economic Forecasting. Blackwell Publishers, Oxford, pp. 322-353.; Fildes, R., Ord, K., 2001. Forecasting competitions: their role in improving forecasting practice and research. In: Clements, M.P., Hendry, D.F. (Eds.), A Companion to Economic Forecasting. Blackwell Publishers, Oxford, pp. 322-353.
[14] Granger, C. W.J., Prediction with a generalized cost of error function, Operational Research, 20, 199-207 (1969) · Zbl 0174.21901
[15] Granger, C. W.J., Combining forecasts—twenty years later, Journal of Forecasting, 8, 167-173 (1989)
[16] Granger, C. W.J., Outline of forecast theory using generalized cost functions, Spanish Economic Review, 1, 161-173 (1999)
[17] Granger, C. W.J.; Newbold, P., Forecasting Economic Time Series (1986), Academic Press: Academic Press New York · Zbl 0642.90001
[18] Granger, C. W.J.; Pesaran, M. H., Economic and statistical measures of forecast accuracy, Journal of Forecasting, 19, 537-560 (2000)
[19] Granger, C. W.J.; Ramanathan, R., Improved methods of combining forecasts, Journal of Forecasting, 3, 197-204 (1984)
[20] Hendry, D. F.; Clements, M. P., Pooling of forecasts, Econometrics Journal, 5, 1-26 (2002) · Zbl 1053.62104
[21] Koenker, R.; Basset, G., Regression quantiles, Econometrica, 46, 33-50 (1978) · Zbl 0373.62038
[22] Laster, D.; Bennett, P.; Geoum, I. S., Rational bias in macroeconomic forecasts, Quarterly Journal of Economics, 114, 293-318 (1999)
[23] Marcellino, M., 2002, Forecast pooling for short time series of macroeconomic variables. Mimeo, IGIER, Bocconi University.; Marcellino, M., 2002, Forecast pooling for short time series of macroeconomic variables. Mimeo, IGIER, Bocconi University.
[24] Marron, J. S.; Wand, M. P., Exact mean integrated squared error, Annals of Statistics, 20, 712-736 (1992) · Zbl 0746.62040
[25] Min, C.-k.; Zellner, A., Bayesian and non-Bayesian methods for combining models and forecasts with applications to forecasting international growth rates, Journal of Econometrics, 56, 89-118 (1993) · Zbl 0800.62800
[26] Newbold, P.; Harvey, D. I., Forecast combination and encompassing, (Clements, M. P.; Hendry, D. F., A Companion to Economic Forecasting (2001), Blackwells: Blackwells Oxford) · Zbl 1180.91232
[27] Newey, W.; Powell, J., Asymmetric least squares estimation and testing, Econometrica, 55, 819-847 (1987) · Zbl 0625.62047
[28] Palm, F. C.; Zellner, A., To combine or not to combine? Issues of combining forecasts, Journal of Forecasting, 11, 687-701 (1992)
[29] Peel, D.A., Nobay, A.R., 1998. Optimal monetary policy in a model of asymmetric central bank preferences. FMG discussion paper 0306.; Peel, D.A., Nobay, A.R., 1998. Optimal monetary policy in a model of asymmetric central bank preferences. FMG discussion paper 0306. · Zbl 0945.91046
[30] Perez-Quiros, G.; Timmermann, A., Business cycle asymmetries in stock returnsevidence from higher order moments and conditional densities, Journal of Econometrics, 103, 259-306 (2001) · Zbl 0972.62101
[31] Raftery, A. E.; Madigan, D.; Hoeting, J. A., Bayesian model averaging for linear regression models, Journal of the American Statistical Association, 92, 179-191 (1997) · Zbl 0888.62026
[32] Rudin, W., Principles of Mathematical Analysis (1964), McGraw-Hill: McGraw-Hill New York · Zbl 0148.02903
[33] Stock, J. H.; Watson, M. W., Forecasting inflation, Journal of Monetary Economics, 44, 293-375 (1999)
[34] Tay, A.; Wallis, K., Density forecastinga survey, Journal of Forecasting, 19, 235-254 (2000)
[35] Varian, H. R., A Bayesian approach to real estate assessment, (Fienberg, S. E.; Zellner, A., Studies in Bayesian Econometrics and Statistics in Honor of Leonard J. Savage (1974), North-Holland: North-Holland Amsterdam), 195-208
[36] Weiss, A. A., Estimating time series models using the relevant cost function, Journal of Applied Econometrics, 11, 539-560 (1996)
[37] West, K. D.; Edison, H. J.; Cho, D., A utility based comparison of some models of exchange rate volatility, Journal of International Economics, 35, 23-46 (1993)
[38] Whittle, P., 1983. Prediction and regulation by linear least square methods. 2nd Edition, Revised. University of Minnesota Press, Minneapolis, MN.; Whittle, P., 1983. Prediction and regulation by linear least square methods. 2nd Edition, Revised. University of Minnesota Press, Minneapolis, MN. · Zbl 0646.62079
[39] Zellner, A., Bayesian estimation and prediction using asymmetric loss functions, Journal of the American Statistical Association, 81, 446-451 (1986) · Zbl 0603.62037
[40] Zhu, L.-X.; Neuhaus, G., Nonparametric Monte Carlo tests for multivariate distributions, Biometrika, 87, 919-928 (2000) · Zbl 1028.62033
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.