我国车损险准备金评估的随机模型及其应用.pdfVIP

我国车损险准备金评估的随机模型及其应用 中文摘要 本文系统研究了车损险准备金评估的许多随机模型：首先讨论了与传统链梯 法估计结果一致的随机模型，然后将其扩展到参数曲线模型和光滑模型。随机 模型的一个主要优势是可以对估计结果的精确度进行测量，其判断指标为均方 误差。本文将上述随机模型应用到我国保险公司车损险的实际数据，并比较了 各个模型得到的结果。结果表明，不同的模型预测的准备金估计值可能很接近， 也可能差距很大，而预测误差也不尽相同。假设分布对计算结果的影响很大， 就本文的数据来说，Gamma 分布结果要好于Poisson 分布的结果，这与国外的研 究结果反差较大。同时，我国的车损险数据通过各个模型得到的预测误差都较 大，预测误差百分比基本上都在70%以上。本文所采用的所有随机模型最终都可 以归入广义可加模型（GAM）一类，只是所采用的平滑参数不同。 关键词：准备金评估；随机模型；链梯法 我国车损险准备金评估的随机模型及其应用 Abstract This paper considers a wide range of stochastic reserving models for use in automobile insurance. It is beginning with stochastic models which reproduce the traditional chain-ladder reserve estimates. The models are extended to consider parametric curves and smoothing models for the shape of the development run-off. The primary advantage of stochastic reserving models is the availability of measures of precision of reserve estimates, and in this respect, attention is focused on the root mean squared error of prediction (prediction error). These models are applied to the automobile claims data of a Chinese insurance company and the different results are compared. The reserves estimated by different models are different. The prediction errors are different too. The distribution assumed in the model is another factor which may influence the result. It is better to choose Gamma distribution than Poisson distribution in the data we used. At the same time, the percentages of prediction error of different models are larger than 70%. In fact，all the models included in this paper can be thought of as the Generalised Additive Models with different smoothing parameters. Key words: Reserving; Stochastic Models; Chain-Ladder 我国车损险准备金评估的随机模型及其应用 目录 第1 章 综述 1 第2 章 准备金评估的随机模型 2 2.1 链梯模型（Chain-Ladder Models ） 2