Comparing Possibly Misspeci ed Forecasts
Comparing Possibly Misspeci ed Forecasts
复制标题
比较可能错误的预测
DOI：
--
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
B. Lieberman
中科院分区：
文献类型：
--
作者：
B. Lieberman
Recent work has emphasized the importance of evaluating estimates of a statistical functional (such as a conditional mean, quantile, or distribution) using a loss function that is consistent for the functional of interest, of which there are an innite number. If forecasters all use correctly specied models free from estimation error, and if the information sets of competing forecasters are nested, then the ranking induced by a single consistent loss function is su¢ cent for the ranking by any consistent loss function. This paper shows, via analytical results and realistic simulationbased analyses, that the presence of misspecied models, parameter estimation error, or nonnested information sets, leads generally to sensitivity to the choice of (consistent) loss function. Thus, rather than merely specifying the target functional, which narrows the set of relevant loss functions only to the class of loss functions consistent for that functional, forecast consumers or survey designers should specify the single specic loss function that will be used to evaluate forecasts. An application to survey forecasts of US ination illustrates the results. Keywords: Survey forecasts, economic forecasting, point forecasting, model misspecication, Bregman distance, proper scoring rules, consistent loss functions. J.E.L. codes: C53, C52, E37. AMS 2010 Classications: 62M20, 62P20. For helpful comments and suggestions I am grateful to the editor (Todd Clark) and two referees, and also Tim Bollerslev, Dean Croushore, Frank Diebold, Tilmann Gneiting, Jia Li, Robert Lieli, Minchul Shin, Allan Timmermann and seminar participants at Boston College, Columbia, Duke, Penn, Princeton, St. Louis Federal Reserve, 8 French Economics conference, NBER Summer Institute, Nordic Econometric Society meetings, and the World Congress of the Econometric Society. Finally, I thank Beatrix Patton for compelling me to just sit quietly and think about this problem. Contact address: Department of Economics, Duke University, 213 Social Sciences Building, Box 90097, Durham NC 27708-0097. Email: andrew.patton@duke.edu. The supplemental appendix for this paper is available at http://econ.duke.edu/sap172/research.html.
Recent work has emphasized the importance of evaluating estimates of a statistical functional (such as a conditional mean, quantile, or distribution) using a loss function that is consistent for the functional of interest, of which there are an innite number. If forecasters all use correctly specied models free from estimation error, and if the information sets of competing forecasters are nested, then the ranking induced by a single consistent loss function is su¢ cent for the ranking by any consistent loss function. This paper shows, via analytical results and realistic simulationbased analyses, that the presence of misspecied models, parameter estimation error, or nonnested information sets, leads generally to sensitivity to the choice of (consistent) loss function. Thus, rather than merely specifying the target functional, which narrows the set of relevant loss functions only to the class of loss functions consistent for that functional, forecast consumers or survey designers should specify the single specic loss function that will be used to evaluate forecasts. An application to survey forecasts of US ination illustrates the results. Keywords: Survey forecasts, economic forecasting, point forecasting, model misspecication, Bregman distance, proper scoring rules, consistent loss functions. J.E.L. codes: C53, C52, E37. AMS 2010 Classications: 62M20, 62P20. For helpful comments and suggestions I am grateful to the editor (Todd Clark) and two referees, and also Tim Bollerslev, Dean Croushore, Frank Diebold, Tilmann Gneiting, Jia Li, Robert Lieli, Minchul Shin, Allan Timmermann and seminar participants at Boston College, Columbia, Duke, Penn, Princeton, St. Louis Federal Reserve, 8 French Economics conference, NBER Summer Institute, Nordic Econometric Society meetings, and the World Congress of the Econometric Society. Finally, I thank Beatrix Patton for compelling me to just sit quietly and think about this problem. Contact address: Department of Economics, Duke University, 213 Social Sciences Building, Box 90097, Durham NC 27708-0097. Email: andrew.patton@duke.edu. The supplemental appendix for this paper is available at http://econ.duke.edu/sap172/research.html.