多指标可加模型及在医疗费用预测中的应用

对医疗费用的建模分析与合理预测是医疗保险费用厘定的基础与根本.医疗费用中的高维附加信息在长期预测中具有重要作用.然而,传统的统计建模方法不适用于处理高维纵向数据下的医疗费用.本文提出部分线性多指标可加模型,对具有高维特征的纵向医疗费用数据进行拟合与预测,并且使用两种不同的降维估计方法进行模型估计,并将该模型应用于一组含...     

基于可调权重距离的最小一乘回归方法

不同时期数据对因变量的影响权重不同,若不考虑数据的时间特性而构建回归模型,可能不一定得到最佳的回归模型.针对经济领域中数据时间跨度大,样本少以及可能存在异常点的特点,提出基于可调权重距离的最小一乘回归方法.建立了可调权重距离的权重系数确定方法,并给出基于MATLAB的模型求解方法.通过某船舶使用费用预测的应用,表明通过方法构建的模型具有更高的精度,值得借鉴.     

零膨胀广义泊松回归模型与保险费率厘定

在保险产品的分类费率厘定中,最常使用的模型之一是泊松回归模型.当损失数据存在零膨胀(zero-in flated)特征时,通常会采用零膨胀泊松回归模型.在零膨胀泊松回归模型中,一般假设结构零的比例参数φ为常数,不受费率因子的影响,这有可能背离实际情况.假设参数φ与费率因子之间存在一定关系,并在此基础上建立了零膨胀广义泊松回归模型,即Z IGP(τ)回归模型.通过对一组汽车保险损失数据的拟合表明,Z IGP(τ)回归模型可以有效地改善对实际数据的拟合效果,从而提高费率厘定结果的合理性.     

零—膨胀泊松回归模型的非参数统计分析及其应用

零膨胀计数数据是当今数据分析的热点问题之一,该类数据的特点是零点过多,目前对这类数据的研究已经比较全面。另外还有些计数数据不仅会出现零点过多的现象,也会同时存在零、一点都过多的情形,如果再用零膨胀计数数据的统计方法去研究,产生的误差较大。目前国内外对零和一都膨胀的数据的研究还比较少,针对这种现象,本文引入零一膨胀泊松回归模型,并用局部多项式核回归法这种非参数统计分析方法对零一膨胀泊松回归模型进行参数估计,这是本文的创新点也是难点,并在求解参数的过程中引进了EM算法和Newton-Raphson迭代对参数近似求解。通过模拟结果可以得出此方法的可行性,最后通过对糖尿病患者数据的实例分析,可以验证此方法的有效性。     

重尾分布下医疗保险保费合理性评估——基于上海市闵行区新农合的实证研究

重尾是医疗费用以及医疗保险损失分布的常见特征之一,本文构建了在重尾分布下,医疗保险经营者科学评估医疗保险保费合理性的模型和方法。当医疗费用面临二阶矩不存在的重尾性下,稳定分布理论中的广义中心极限定理可以取代古典的中心极限定理去评估医疗保险保费的合理性。本文最后用2008年上海市闵行区新型农村合作医疗的住院医疗费用数据进行了实证分析,全面探测了医疗费用的重尾性以及在尾部指标的基础上,估计了闵行区新农合筹资的合理性.     

数据预处理对替代数据检验方法的影响

替代数据检验法是检验时间序列中是否存在确定性非线性成分的重要统计方法.通过研究差分和数据平滑运算对替代数据检验方法的影响,指出常用的线性滤波等数据预处理步骤破坏了序列的静态性质,从而会导致对零假设的错误拒绝.因此,建议应该直接利用原始时间序列而非应用了差分等非静态滤波运算后的时间序列生成替代数据,再进行假设检验,以免造成对零假设的错误拒绝.     

缺失数据的偏差校正(系列三)

调查中的缺失数据会造成估计量的偏倚。有一些简单易行的对数据进行调整的方法 ,如果使用得当 ,可以减小由于缺失数据造成的估计量偏倚。本文介绍了三种常用的方法 :即 ,再抽样调整 ;多次调查数据调整和相关推估法     

广义网络向量自回归

随着社交网络平台的快速发展,带有网络结构的时序数据越来越多.为拟合用户行为的动态变化,网络向量自回归模型被提出.模型最早研究的是连续型因变量.然而实际数据常观测到离散型因变量.由此,本文提出广义网络向量自回归模型.模型假设存在一个潜在的连续型变量,决定了可观测到的离散型因变量的取值.为了估计和推断模型,本文提出了MCMC (Markov chain Monte Carlo)算法并通过随机模拟进行验证.最后,使用某社交网络平台上的两个真实的数据案例作为例证.     

HMO市场结构影响下的美国医疗费用预测分析

分析了美国HMO（Health Maintenance Organization）市场结构主要指标及部分医疗和社会经济指标对美国医疗费用的影响,采用1995-2007年数据,利用主成分分析（PCA）方法与BP神经网络构建预测模型,对美国支出在医院方面的医疗费用进行拟合及预测,预测结果与实际值之间的相对误差小于0.25%,表明可基于该模型考察在HMO市场结构影响下的美国医疗费用.     

多元统计分析(Ⅷ)

ξ7.多因变量逐步回归 多元回归分析是多元统计中应用最广的方法.“多元”可以理解为多个自变元(只有一个因变元),也可以理解为自变量和因变量都是多个的情形.鉴于只有一个因变量的多元回归己众所周知,因此本节的重点是讨论含有多个因变量的回归及其逐步算法 7.1多因变量回归分析 1.模型 设x1,…,xp是p是自变量,y1,…,yq是q个因变量,并有如下的线性关系:其中εj是随机误差,βij是回归系数.回归分析问题是根据变量x与y的n次已知观测数据去估计回归系数,并对回归系数作统计检验等等. 在回归模型中,随机误差总假设没有系统偏差,即均值为零,所以…     

国家审计对政府卫生支出的影响及异质性研究——基于贝叶斯分位数回归模型

本文利用2007~2016年省级数据,基于贝叶斯分位数回归模型研究了国家审计对政府卫生支出的影响,及不同政府卫生支出水平下各影响因素的异质性效应。结果表明,国家审计对政府卫生支出的腐败行为具有显著的治理功能,国家审计的投入力度越大,其监督、预防、揭示和抵御功能发挥得越好,越有助于提高政府卫生支出水平。此外,不同的政府卫生支出水平,国家审计治理的影响程度具有明显异质性效应,且各影响因素的系数变化具有显著性差异。因此,为加强腐败治理促进政府卫生支出,不仅需要注重国家审计顶层设计的落地,加强政府多方部门合作推进协同审计,而且应根据具体的政府卫生支出水平做出相应的政策调整以避免地方“政策趋同”带来的不利。     

Computational estimation skill of preservice teachers: operation type and teacher view

Despite the importance of computational estimation skill for the improvement of number sense, little research exists on preservice teachers’ estimation skills and their view on estimation in the US context. This study examined the computational estimation skill of 58 preservice elementary teachers (PSTs) and its relationship to their views of the meaning of estimation and the importance of teaching it. Three sets of instruments were used: an estimation task, a computational task, and a belief survey. Results indicated that PSTs performed differently depending on the types of operations on the estimation test. It was also found that different types of problems elicited different strategies. Furthermore, the intervention of the study, along with five other factors were found to significantly correlate with estimation skills. The five factors include PSTs’ mathematical knowledge, their reported confidence about estimation skills, their self-reported knowledge about calculator use in instruction, their views of estimation in teaching mathematics, and their definition of estimation. A negative correlation was documented for the knowledge of calculator use in instruction, and positive correlations were present for other factors. Implications are discussed in accordance with these findings.     

连续性抽样调查理论研究综述

从国外近60多年来的理论及其应用研究情况来看,连续性抽样调查是一个具有极大理论研究价值的新领域,在我国也具有广阔的应用价值。本文选择连续性抽样调查作为研究对象,对国内外已有的相关研究成果进行理论化、系统化的研究综述,并重点总结了各类连续性抽样设计与抽样估计方法,进一步归纳出存在的问题及未来继续研究的新趋势,另外也为该理论在我国实际调查中的应用研究奠定扎实的理论基础,使我国统计调查工作少走弯路,尽快与国外统计调查工作接轨。     

基于轮换样本连续性调查的校准组合估计方法研究

校准估计是抽样调查中比较常用的一种利用辅助信息提高估计量精度的方法。回归组合估计量作为轮换样本连续性调查中使用的一种有效的估计量,是可以通过校准程序得到的。基于回归组合估计量和校准程序之间的关系,本文提出了轮换样本连续性抽样调查条件下的不同校准组合估计量及其方差估计。校准组合估计量的主要思想是在校准估计程序中将拼配样本和非拼配样本的辅助信息进行不同的组合利用。本文利用美国现时人口调查的微观数据进行数值模拟,来比较不同校准组合估计量的估计效率,模拟结果表明两步校准组合估计量和两步校准双组合估计量的表现相似,且估计精度都高于H-T估计量及回归组合估计量;而两步校准组合估计量由于其简便性更适合应用于实践中。最后以我国农村住户连续性抽样调查为例,设计一套符合我国实际的轮换样本连续性调查方案,并将提出的校准组合估计量运用于估计阶段,为中国政府统计调查提供一定的借鉴和参考.     

Research topics in discrete estimation of distribution algorithms based on factorizations

In this paper, we identify a number of topics relevant for the improvement and development of discrete estimation of distribution algorithms. Focusing on the role of probability distributions and factorizations in estimation of distribution algorithms, we present a survey of current challenges where further research must provide answers that extend the potential and applicability of these algorithms. In each case we state the research topic and elaborate on the reasons that make it relevant for estimation of distribution algorithms. In some cases current work or possible alternatives for the solution of the problem are discussed.     

湖南省公共医疗卫生支出效率及其影响因素实证分析

利用DEA-Tobit两阶段分析法,计算出2009-2013年5年间湖南省14个地级市政府公共医疗卫生支出的综合技术效率值、纯技术效率值、规模效率值三种效率值,分析出湖南省各地级市政府公共医疗卫生支出所处规模报酬阶段,并对反映卫生支出资金配置的综合技术效率水平的外部影响因素加以回归分析.结果发现:湖南省各地区公共医疗卫生效率水平整体水平偏低并且存在明显的差异性,除长沙以外的其他地级市政府公共医疗卫生支出均处于不同程度的非充分效率水平.湖南省各地区人均生产总值及城市化水平对公共医疗卫生支出效率有显著的促进作用.教育水平、人口密度、居民人均可支配收入对湖南省公共医疗卫生支出效率的提高有阻碍作用.     

The relationship between budgetary expenditure and economic growth in Poland

This paper investigates the association between different kinds of budgetary expenditure and economic growth of Poland. The empirical analysis makes use of linear and nonlinear Granger causality tests to evaluate the applicability of Wagner’s Law and that of the contrasting Keynesian theory. We employ aggregate and disaggregate data with the sub-categories of most important budgetary expenditure, including health care and social security, education and science, national defence and public security expenditure and government administration expenditure for the period Q1 2000 to Q3 2008. This causality analysis indicates that total relation between budgetary expenditure and economic growth is consistent with Keynesian theory. The results of our computations have important policy implications. In case of Poland the health care expenditure was found to be as important for economic growth as expenditures on education and science. Furthermore, in order to stimulate economic growth, Polish government should consider reallocating some of national defence, public security and government administration expenditure to health care, social security, education and science expenditure.     

基于Panel Data的地区财政支出结构优化模型研究

本文用平面数据(PanelData)的协整理论和误差修正模型、多目标规划等方法,利用1994—2001年中国各地区财政支出结构的数据,构建了地区财政支出结构优化模型,并对河北省2000年和2001年的财政支出结构进行了实证分析,提出了优化方案。结论显示,在财政支出总量不变的前提下,模型拟合取得了满意的效果。     

Detection of heterogeneity and estimation of population characteristics from the field survey data: 1987/88 Japanese feasibility study of the southern hemisphere Minke whales

To get reliable information of the age structure of whale population, Japan conducted a feasibility study of scientific research in the Antarctic in 1987/88. Though the sample was not large enough, it was the first data free from the problem of selectivity and whaling ground bias. From the analysis, it was found that the biological characteristics are highly heterogeneous spatially or other ways. Considering this, we recognize that the survey should be designed to collect the sample from the whole research area uniformly to obtain unbiased estimates of population characteristics. However, in an actual biological field survey, it is difficult to keep the sampling fractions thecisely the same for each sampling units. Therefore, it is important to detect the heterogeneity in the sample, and poststratify the data corresponding to the heterogeneity. The methodology of the estimation and model evaluation presented here will be useful for the development of biological field survey in general.     

Can R&D expenditure avoid corporate bankruptcy? Comparison between Japanese machinery and electric equipment industries using DEA–discriminant analysis

This study compares data envelopment analysis–discriminant analysis (DEA–DA) with Altman’s financial ratio analysis to identify the position of DEA–DA in financial performance analysis. Then, this study applies DEA–DA to examine whether Research and Development (R&D) expenditure influences the financial performance of Japanese machinery industry and electric equipment industry. The investigation of DEA–DA identifies that the R&D expenditure makes a positive impact on the financial performance of Japanese machinery industry, but it yields a negative impact on Japanese electric equipment industry. The result implies that the influence of R&D expenditure on financial performance (including the avoidance of bankruptcy) depends upon the type of a manufacturing industry. A rationale regarding why such a discrepancy has occurred between the two Japanese manufacturing industries is because the life cycle of electric equipments is shorter than that of the machinery products. Furthermore, the electric equipment industry faces more fierce competition than the machinery industry. This study suggests that the Japanese electric equipment industry needs R&D expenditure for competition in its global market. However, it is a high risk and high return investment. In contrast, the Japanese machinery is a technologically mature industry where the R&D expenditure influences positively its financial performance. In this sense, the R&D expenditure is a low risk and necessary investment.