论文部分内容阅读
非寿险分类费率的厘定通常采用的方法有单项分析法、最小偏差法和广义线性模型,特别是后面两种方法在非寿险实务中应用十分广泛,精算文献中对这两种方法的理论和应用研究也较多,但对二者的比较研究较少。本文首先对最小偏差模型和广义线性模型进行了简要介绍,之后对这两种分类费率模型进行了系统的比较研究,总结了它们各自的优缺点以及二者之间的一些等价关系,最后通过一组实际的汽车保险数据讨论了它们的应用。
Non-life insurance classification rates commonly used methods are single analysis method, the minimum deviation method and the generalized linear model, especially the latter two methods are widely used in non-life insurance practice, actuarial literature on these two methods of theory and There are more applied research but less research on the two. This paper first introduces the minimum deviation model and the generalized linear model briefly, and then compares the two classification rate models systematically, summarizes their respective advantages and disadvantages and some equivalence relations between them, finally Their use is discussed with a set of actual car insurance data.