半参数广义线性模型的影响分析与异常点检验

统计诊断就是对统计推断方法解决问题的全过程进行诊断，而影响分析是统计诊断中十分重要的分支．本文针对半参数广义线性模型，证明了数据删除模型和均值漂移模型的等价性定理，给出了诸如广义Cook距离等诊断统计量并研究了异常点的Score检验统计量，最后通过实例验证了本文给出的诊断方法的有效性。     

偏正态数据下联合位置与尺度模型的统计诊断

本文研究偏正态数据下联合位置与尺度模型,考虑基于数据删除模型的参数估计和统计诊断,比较删除模型与未删除模型相应统计量之间的差异.首次提出基于联合位置与尺度模型的诊断统计量和局部影响分析.通过模拟研究和实例分析,给出不同的诊断统计量来判别异常点或强影响点,研究结果表明本文提出的理论和方法是有用和有效的.     

基于Pena距离的双重广义线性模型的统计诊断

本文主要研究双重广义线性模型,考虑基于数据删除模型的参数估计和统计诊断,比较删除模型与未删除模型相应的诊断统计量之间的变化.首次提出基于双重广义线性模型下的Pena距离.通过一些模拟研究以及实例分析,比较不同诊断统计量判别异常点或强影响点的差异,研究结果表明本文提出的理论和方法是行之有效的.     

m维AR(p)模型的统计诊断

统计诊断就是探查对统计推断（如估计或预测等）有较大影响的数据从而对全过程数据进行诊断．本文应用基于数据删除模型得到二维AR（1）模型的参数估计诊断公式,给出了Cook统计量的计算公式,进而推广到m维AR（p）模型的情形．     

基于杠杆值大数据集抽样的异常点诊断

本文主要研究大数据集下利用杠杆值抽样后的异常点诊断问题。首先讨论了数据删除模型中参数估计的统计性质,构造了四种异常点诊断统计量;其次,根据均值漂移模型的漂移参数的假设检验问题,构造了三种检验统计量;最后,通过模拟和实证数据分析结果得出本文的结论—异常点诊断对于基于杠杆值的大数据集抽样估计起到重要的影响作用。     

Logistic回归模型的统计诊断

统计诊断的主要任务就是通过诊断统计量检测已知观测数据在用既定模型拟合时的合理性,主要是找出数据当中的异常点或强影响点。本文主要研究Logostic回归模型的诊断统计量和诊断统计图。用牛顿迭代法给出Logistic回归模型的极大似然估计值,根据扰动模型得到传统的诊断统计量,结合残差、杠杆值和系数变化三者构造新的诊断统计量,绘制新的诊断统计图,通过模拟研究说明新的诊断统计量的有效性,最后用一个实际案例说明新的诊断方法的应用并进一步验证其优越性。     

线性回归诊断的若干问题

本文对于线性回归诊断提出了几种新的模型和方法。我们首次研究了方差加权和均值漂移的混合模型,得到了相应的诊断统计量。本文还引入了罚函数方法,并以此为工具,讨论了若干有偏估计的影响度量,最后,本文提出了基于重心的诊断统计量,对于识别异常点有较好的效果。     

基于模糊Cook距离的模糊线性回归模型的统计诊断

针对确定输入、模糊输出的模糊线性回归分析模型,采用最小二乘法,讨论了模糊线性回归模型的数据删除模型的参数估计,将建立在确定性数据基础上的线性回归模型统计诊断量Cook距离推广到模糊线性回归分析模型中,构造了统计诊断量—模糊Cook距离,通过数值模拟和对实际例子的研究,识别出其中的强影响点,得出与其它方法相同的结论,表明本文构造的统计诊断量是有效的,且应用比其它方法更方便.     

Logistic回归模型的影响分析

Logistic回归模型的影响分析是Logistic回归诊断研究中的重要内容。常用的分析方法都是轮换地删除数据点后的逐步判断,而这个判断的过程主要体现在模型的诊断图上。鉴于此,通过构造诊断统计量来有效地开发诊断图成为影响分析的核心内容,并由此能较为准确地探寻出模型的强影响点。本文通过对Logistic回归模型帽子矩阵的分解以及对轮换地删除数据点后的系数估计的相对变化量进行加权,得出Logistic回归模型诊断图使其能比传统的诊断图更准确地判断出模型的强影响点。     

一个关于线性模型结构变化预测的推断

利用统计诊断的一些思想，从Bayes预测理论的角度分析线性模型中的结构变化．考察两相回归模型其中诸yi是观察值，凡是回归变量的已知向量（p×1）,Oj（j＝1，2）是未知参数向县（p×1），是未知参数，诸εi是相互独立的．m是未知参数称为变点．我们主要对m感兴趣．实际上，在模型（1．1）中的统计推断之前，我们不知道哪个参数变化．本文结合统计诊断的一些思想和Dayes观点，利用基于条件预测奇异诊断（以下简记为CPDD）和Kullback-Leibler散度两种方法，来研究线性模型的结构变化．这些方法不限于任何条件，且能找出哪些参数变化；哪…     

Diagnostic Measures for Censored Linear Models based on Empirical Likelihood Method

In this paper, the diagnostic measures for censored linear models are studied based on the empirical likelihood method. First, the diagnostic measures for linear models are studied; Then, the censored linear models are converted to linear models, and the diagnostic measures for converted models are studied; Last, simulation studies and real data analysis are given to illustrate the validity of statistical diagnostic measures.     

基于因素空间理论的故障诊断数学模型及其应用

本文利用汪培庄教授提出的因素空间理论,为诊断问题下了一个新的数学定义,以此为基础,给出了故障诊断的数学模型。最后讨论了故障诊断专家系统的构建方法及其应用。     

The Diagnosis of Deep-Vein Thrombosis: An Application of Decision Analysis

Using information from the medical literature on the accuracy and complications of diagnostic tests and therapy, a decision-analysis model is developed and used to evaluate alternative diagnostic strategies for deep-vein thrombosis. With the help of an integrated computer-software package, the probability of death or major complication of different diagnostic strategies is computed, and the strategies exhibiting the least morbidity and mortality are identified. The sensitivity of the results to changes in the parameters of the model are explored. The work provides surprising insights into the role of diagnostic tests.     

Technical diagnostic of a fleet of vehicles using rough set theory

The paper presents a process of technical diagnostic applied to a fleet of vehicles utilized in the delivery system of express mail. It is focused on evaluation of diagnostic capacity of particular characteristics, reduction of a set of initially selected characteristics to a minimal and satisfactory subset, recognition of a technical condition of vehicles resulting in their condition-based classification. In addition, the decision rules facilitating technical diagnostic and management of a fleet of vehicles are generated and utilized. N-fold cross validation is applied to estimate the efficiency of the decision rules. The rough set theory is applied to support the diagnostic process of vehicles. Classical rough set (CRS) theory is compared with the dominance-based rough set (DRS) approach. The results of computational experiments for both approaches are compared.     

半参数非线性模型的统计诊断与影响分析

本文系统研究了半参数非线性回归模型的统计诊断与影响分析方法;得到了一系列诊断统计量,两个实际数值例子验证了本文给出的诊断方法的有效性。     

Diagnostic assessment of preparedness of level one sports science students for biomechanics modules

The primary objective of this study was to investigate the use of a diagnostic test to assess the prepardness of level one students for a sports biomechanics module. During their first week at university, a cohort of 108 students completed a diagnostic test at the end of their first lecture in sports biomechanics, with no prior notice. Upon completion of the 12-week module, the students sat the same diagnostic test, again with no prior notice. The results from the initial test were used to identify areas that required emphasis and additional resources during delivery of the module. The comparison of test results from the two sittings was used as a measure of the level of success of the module in increasing the level of student understanding. It is concluded that the design of a diagnostic test specific to a module can be used both to inform subsequent teaching and to assess success of teaching methods.     

机械故障模糊诊断中模糊矩阵的可视化处理与分析

通过对机械故障诊断中的模糊矩阵及采用不同数学模型运算后的结果进行可视化处理,得到二维图谱和三维图谱,使故障与征兆之间的关系更加明确     

A Markov Chain Monte Carlo Convergence Diagnostic Using Subsampling

Abstract

A new diagnostic procedure for assessing convergence of a Markov chain Monte Carlo (MCMC) simulation is proposed. The method is based on the use of subsampling for the construction of confidence regions from asymptotically stationary time series as developed in Politis, Romano, and Wolf. The MCMC subsampling diagnostic is capable of gauging at what point the chain has “forgotten” its starting points, as well as to indicate how many points are needed to estimate the parameters of interest according to the desired accuracy. Simulation examples are also presented showing that the diagnostic performs favorably in interesting cases.     

皮肤毛孔照片诊断标准评价的潜在分类变量模型研究

本文在无金标准情况下探讨皮肤毛孔标准照片制定的合理性和可行性,对医师诊断正确性进行评价。按照毛孔粗大程度制定分类为5水平的毛孔标准照片。对128名女性志愿者制作鼻翼毛孔照片,5位年资相近的皮肤科医师按照诊断标准和标准照片对128例自愿者照片进行独立的等级评分。诊断结果数据采用潜在分类变量模型(Latent Class Model,LCM)进行分析,分别拟合5位医师诊断条件概率一致的模型和诊断条件概率不一致的模型。计算医师诊断的条件概率和后验概率。潜变量分析结果提示诊断标准过于细化且分类模糊,依据条件概率将原始分类重新划分为3类的模型较好地拟合了诊断数据。运用客观和准确的能够真实反应和区分个体情况的诊断标准是诊断试验评价的基础和前提。潜在分类模型能够有效地处理无金标准的诊断重复性或一致性研究数据。