報告題目：Forecast Interpretation and Evaluation

報告時間：2018年4月3日上午10:00

報告地點：旭日樓306教室

主講人：杜海良博士

主講人簡介：

杜海良，統計學博士，2009年博士畢業于倫敦政治經濟學院。畢業以後至2013年在倫敦政治經濟學院時間序列研究中心和氣候變化經濟政策研究中心擔任研究員從事時間序列分析以及非線性動力學理論研究。2014年加入芝加哥大學氣候能源決策研究中心從事氣候模型可靠性分析。于2017加入杜倫大學數學科學系從事能源系統不确定性量化分析。2018 被杜倫大學任命為助理教授。

報告簡介：

The evaluation of forecast performance plays a central role both in the interpretation and in the use of forecast systems and their development. Many forecast systems are available, but evaluations of their performance are not standardized, with many different scores being used to measure different aspects of performance. Ensemble interpretations which interpret a probability forecast as a point forecast (a delta function such as the ensemble mean) or as a collection of delta functions (reflecting, for example, the position of each ensemble member) may provide misleading estimates of skill in nonlinear systems as they fail to consider all the probabilistic information available. Even when the discussion is restricted to proper scores, there remains considerable variability between scores in terms of their sensitivity to outcomes in regions of low (or vanishing) probability; proper scores need not rank competing forecast systems in the same order when each forecast system is imperfect. The locality property is explored to further distinguish skill scores. The only local proper score, the logarithmic score, has an immediate interpretation in terms of bits of information. Nonlocal proper scores considered are shown to have properties that could produce counter intuitive evaluations. It is suggested that the logarithmic score always be included in the evaluation of probabilistic forecasts.