期刊名称：Journal of Agricultural and Resource Economics
印刷版ISSN：1068-5502
出版年度：2015
卷号：40
期号：2
页码：306-324
出版社：WAEA
摘要：This article develops a procedure for weighting historical loss cost experience based on longertime-series weather information. Using a fractional logit model and out-of-sample competitions,weather variables are selected to construct an index that allows proper assessment of the relativeprobability of weather events that drive production losses and to construct proper “weatherweights” that are used in averaging historical loss cost data. A variable-width binning approachwith equal probabilities is determined as the best approach for classifying each year in the shorterhistorical loss cost data used for rating. When the weather-weighting approach described aboveis applied, we find that the weather-weighted average loss costs at the national level are differentfrom the average loss costs without weather weighting for all crops examined.
