Insurance Premium Prediction via Gradient Tree-Boosted Tweedie Compound Poisson Models

The Tweedie GLM is a widely used method for predicting insurance premiums. However, the structure of the logarithmic mean is restricted to a linear form in the Tweedie GLM, which can be too rigid for many applications. As a better alternative, we propose a gradient tree-boosting algorithm and apply it to Tweedie compound Poisson models for pure premiums. We use a profile likelihood approach to estimate the index and dispersion parameters. Our method is capable of fitting a flexible nonlinear Tweedie model and capturing complex interactions among predictors. A simulation study confirms the excellent prediction performance of our method. As an application, we apply our method to an auto-insurance claim data and show that the new method is superior to the existing methods in the sense that it generates more accurate premium predictions, thus helping solve the adverse selection issue. We have implemented our method in a user-friendly R package that also includes a nice visualization tool for interpreting the fitted model.     

贸易开放度、货币供应量与中国通货膨胀关系的实证检验

在全球化背景下,贸易开放度和通货膨胀的关系成为国际经济学的热点I＇-7题。本文运用1996年到2008年的月度时间序列数据,在VAR模型的基础上,研究了贸易开放度、货币供应量与通货膨胀的动态关系。结果表明：贸易开放度、货币供应量是影响我国通货膨胀的重要因素,贸易开放度的提高,增加了广义货币供应量,进一步形成物价上涨的压力。     

Impact of missing data on type 1 error rates in non‐inferiority trials

In this paper, a simulation study is conducted to systematically investigate the impact of different types of missing data on six different statistical analyses: four different likelihood‐based linear mixed effects models and analysis of covariance (ANCOVA) using two different data sets, in non‐inferiority trial settings for the analysis of longitudinal continuous data. ANCOVA is valid when the missing data are completely at random. Likelihood‐based linear mixed effects model approaches are valid when the missing data are at random. Pattern‐mixture model (PMM) was developed to incorporate non‐random missing mechanism. Our simulations suggest that two linear mixed effects models using unstructured covariance matrix for within‐subject correlation with no random effects or first‐order autoregressive covariance matrix for within‐subject correlation with random coefficient effects provide well control of type 1 error (T1E) rate when the missing data are completely at random or at random. ANCOVA using last observation carried forward imputed data set is the worst method in terms of bias and T1E rate. PMM does not show much improvement on controlling T1E rate compared with other linear mixed effects models when the missing data are not at random but is markedly inferior when the missing data are at random. Copyright © 2009 John Wiley & Sons, Ltd.     

From Mass Production to Mass Customization: Hindrance Factors,Structural Inertia,and Transition Hazard

Research on mass customization has largely overlooked the issue of organizational change associated with the mass production‐to‐mass customization transition. To address this gap in the literature, we conduct a longitudinal case study of a manufacturing facility belonging to a division of a Fortune 1000 discrete manufacturing firm as it seeks to transition from mass production to mass customization. We empirically identify five factors hindering the mass production‐to‐mass customization transition within the research site and articulate five corresponding generalizations explaining how and why these hindrance factors relate to the mass production‐to‐mass customization transition hazard beyond the research site (i.e., how and why the five hindrance factors, in general, threaten the likelihood of a successful mass production‐to‐mass customization transition). We then theoretically validate the five hindrance factors and corresponding generalizations by mapping them onto the antecedents and tenets of structural inertia theory. We conclude with a brief discussion of the scientific and pragmatic significance of the findings and highlight opportunities for future research.     

基于转轨经济的债务期限结构宏观影响因素研究

根据交易成本理论和预期理论,对我国的经济发展水平、通货膨胀、货币供应量、宏观税负等经济总量指标与企业债务期限结构的关系进行经验检验,结果表明:通货膨胀率、国内生产总值增长率和货币供应量均与债务期限呈负相关关系,宏观税负与债务期限正相关,而且相关性都很显著.可见在转轨经济时期,我国上市公司的债务期限除受企业规模、资产期限、成长性等企业内部特征影响外,受宏观经济因素的影响也很显著.     

我国农产品价格波动的影响趋势分析

采用投入产出技术,根据已编制的1981年、1983年、1987年、1990年、1992年、1995年18个部门1990年可比价投入产出表和采用单缩法调整的1997和2000年18个部门1990年不变价投入产出表,从成本推动的角度测算了中国不同年份农产品价格上涨1%对其他部门价格的影响程度和对我国物价总水平的影响程度,并对其影响趋势进行分析。结果表明,物价总水平受农产品价格上涨影响的总体趋势是逐渐下降的。并根据这一规律对农产品价格波动的影响趋势进行短期预测,预测结果显示,农产品价格上涨1%,2005年将导致物价总水平上涨0.12%,到2010年这一影响将降至0.09%。     

我国科技体制建设的基本历程及"路径依赖性"

20世纪我国科学技术体制建设的基本历程可以粗线条地划分为初创时期、建设时期和改革时期三个阶段,并先后历经了科学体制雏形、国防优先的高度集中的科学技术体制、市场导向的不完全性的科学技术体制三种不同的历史形态.特定的社会历史进程形成了我国科学技术体制建设的"路径依赖性",主要是赶超和模仿的"情结"、政府行政主导的计划运行模式和偏好科学技术"生产力"功能的价值选择机制.     

录像机鼓软件伺服模型及相关系数的确定

提出了用于录像机软件伺服控制系统设计的鼓伺服系统模型；针对这种模型计算和测试了所需要的参数，又提出了用计算机辅助设计和分析技术建立三维实体模型，快速准确计算磁鼓组件物理参数的新方法，确定出相关系数；并用实验验证了理论分析计算结果，最后建立了鼓电机的等效电路模型。     

Effects of sleep inertia on cognitive performance following a 1-hour nap

This study investigated the effects of a 1-h nap on subsequent performance in spatial memory (SM) and logical reasoning (LR) tasks. The objective was to evaluate the duration of the effects of sleep inertia (SI). The performance was measured in two independent groups of subjects. The 1-h nap took place at 00:00 h in group 1 and at 03:00 h in group 2. In each task, the experimental design comprised one no-nap condition in which subjects had no sleep before the night tests, and a nap condition that comprised the 1-h nap followed by the test sessions. To measure the duration of SI effects, the subjects were tested in two 30-min sessions and the data in each session were analysed in sub-units of time of 3 min each. In each task the results showed no effects on accuracy, and no circadian effects of napping were found. In each task, analyses of pooled data of the two groups showed that the performance in the 1-h nap condition exhibited significant reductions of speed immediately following awakening, when compared with no-nap, reflecting SI effects. In SM, the slowing lasted 24 min, and 27 min in LR. Practical implications of the results are discussed.     

开放式基金净值增长率被拉升了吗?——中国证券市场日历效应检验

本文旨在研究基金净值增长率在月末、季末、年末最后1个交易日是否被显著地拉升而表现出一定的日历效应.首先引入虚拟变量进行回归分析,然后讨论不同业绩组的日历末表现以及前后10个交易日的净值增长率走势.结果表明,实证支持基金日历末净值增长率异常增大的原假设.此外还发现,净值增长率在月末、季末前后10个交易日明显呈现一个由低点逐渐增大,然后回落的趋势.