00000nam##2200000za#4500 9.615728 CaOODSP 20211126112847 ta 150406|2001||||xxc||||| f|0| 0 eng|d 1192-5434 CaOODSP eng n-cn--- FB3-2/101-12E Bank of Canada. Evaluating linear and non-linear time-varying forecast-combination methods / by Fuchun Li and Greg Tkacz. Ottawa - Ontario : Bank of Canada 2001. v, 15p. : figs., graphs, references ; 28 cm. Working paper 1192-5434 2001-12 "This paper evaluates linear and non-linear forecast-combination methods. Among the non-linear methods, we propose a nonparametric kernel-regression weighting approach that allows maximum flexibility of the weighting parameters. A Monte Carlo simulation study is performed to compare the performance of the different weighting schemes."--Abstract. This paper evaluates linear and non-linear forecast-combination methods. Among the non-linear methods, we propose a nonparametric kernel-regression weighting approach that allows maximum flexibility of the weighting parameters. A Monte Carlo simulation study is performed to compare the performance of the different weighting schemes.--Abstract Résumés en français Softcover 01-33 2001-08-17 Economic forecasting gcpds Economic analysis gcpds Tkacz, Greg Li, Fuchun Evaluating linear and non-linear time-varying forecast-combination methods / (CaOODSP)9.571567 Working paper, 1192-5434 2001-12 (CaOODSP)9.514622