Audrino, Francesco Barone-Adesi, Giovanni 2006-07-11 A multivariate methodology based on Functional Gradient Descent to estimate and forecast time-varying expected bond returns is presented and discussed. Backtesting this procedure on US monthly data, empirical evidence of its strong forecasting potential in terms of the accuracy of the predictions is collected. The proposed methodology clearly outperforms the classical univariate analysis used in the literature. application/pdf https://localhost:5000/ark:/12658/srd1318146 https://susi.usi.ch/global/documents/318146 https://susi.usi.ch/documents/318146/files/baroneadesi_CSDA_2006.pdf eng info:eu-repo/semantics/altIdentifier/doi/10.1016/j.csda.2006.07.024 info:eu-repo/semantics/altIdentifier/ark/12658/srd1318146 info:eu-repo/semantics/openAccess License undefined Computational statistics & data analysis. - Elsevier. - 2006, vol. 51, no. 4, p. 2267-2277 Term structure bond returns functional gradient descent semi-parametric VAR-GARCH models info:eu-repo/classification/udc/33 A dynamic model of expected bond returns : a functional gradient descent approach http://purl.org/coar/resource_type/c_6501