基于Box-Cox变换和随机系数回归的非线性退化数据建模方法

变换方法是处理设备非线性退化建模与剩余寿命预测的一种重要方式和可行途径,目前常见的变换方法主要为对数变换和时间尺度变换,其适用范围有限。鉴于此,文章提出一种基于Box-Cox变换(Box-Cox transformation,BCT)的非线性退化数据建模方法。首先,采用BCT对非线性退化数据进行变换,将变换后的退化数据通过线性随机系数回归模型进行建模。然后,通过构建观测数据的概率密度函数,利用极大似然估计对于BCT中的模型参数进行辨识,并运用Bayesian理论对参数进行在线更新实现退化模型的动态校准。最后,分析经过BCT后的锂电池和轴承实际退化数据,其线性度与相关系数最高分别提升69.63%、9.19%,证明文章方法可行,具有潜在的工程应用价值。

基于互Box-Cox变换和Markov链风速云模型的发电系统充裕度评估

为准确计及风速随机性和自相关性对风电并网系统充裕度的影响,建立基于互Box-Cox变换和Markov链的风速云模型,并将该模型与时序Monte Carlo模拟法结合,提出计及风速随机性和自相关性的风电并网系统充裕度评估方法。仿真结果表明,所提模型产生的仿真风速样本与实测风速样本具备相似的概率分布特性和自相关性,所提方法可较精确地评估风电并网系统充裕度及风电容量可信度。

Forecasting Practice from Box-Cox Transformation Models

In this paper, forecasting analysis to Box Cox transformation models with a practical example is considered. Based on chosen generalized functional form, variables influencing passenger are selected by statistic mechanism, not just by subjective judgment or dependent on certain specified model, and forecasting models are constructed. Comparing with typical linear regression forecasting models, nonlinear forecasting models are more effective and precise. Based on collecting data and final forecasting models, forecasting results are obtained and forecasting errors are analyzed. Finally, some helpful conclusions can be drawn from this study.

Comparison of the Length of Stay and Medical Expenditures among Japanese Hospitals for Type 2 Diabetes Treatments: The Box-Cox Transformation Model under Heteroscedasticity

In this paper, we analyzed length of stay (LOS) in hospitals and medical expenditures for type 2 diabetes patients. LOS was analyzed by the power Box-Cox transformation model when variances differed among hospitals. We proposed a new test and consistent estimator. We rejected the ho-moscedasticity of variances among hospitals, and then analyzed the LOS of 12,666 type 2 diabetes patients hospitalized for regular medical treatments collected from 60 general hospitals in Japan. The variables found to affect LOS were age, number of comorbidities and complications, introduced by another hospital, one-week hospitalization, 2010 revision, specific-hospitalization-period (SHP), and principal diseases E11.5, E11.6 and E11.7. There were surprisingly large differences in ALOS among hospitals even after eliminating the influence of characteristics and conditions of patients. We then analyzed daily medical expenditure (DME) by the ordinary least squares methods. The variables that affected DME were LOS, number of comorbidities and complications, acute hospitalization, hospital’s own outpatient, season, introduced by another hospital, one-week hospitalization, 2010 revision, SHP, time trend, and principal diseases E11.2, E11.4 and E117. The DME did not decrease after the SHP. After eliminating the influences of characteristics and conditions of patients, the differences among hospitals were relatively small, 12% of the overall average. LOS is the main determinant of medical expenditures, and new incentives to reduce LOS are needed to control Japanese medical expenditures. Since at least 99% of patients require medical care after leaving the hospital, systems that take proper care of patients for long periods of time after hospitalization are absolutely necessary for efficient treatment of diabetes.

Identifying Unusual Observations in Ridge Regression Linear Model Using Box-Cox Power Transformation Technique

The use of [1] Box-Cox power transformation in regression analysis is now common;in the last two decades there has been emphasis on diagnostics methods for Box-Cox power transformation, much of which has involved deletion of influential data cases. The pioneer work of [2] studied local influence on constant variance perturbation in the Box-Cox unbiased regression linear mode. Tsai and Wu [3] analyzed local influence method of [2] to assess the effect of the case-weights perturbation on the transformation-power estimator in the Box-Cox unbiased regression linear model. Many authors noted that the influential observations on the biased estimators are different from the unbiased estimators. In this paper I describe a diagnostic method for assessing the local influence on the constant variance perturbation on the transformation in the Box-Cox biased ridge regression linear model. Two real macroeconomic data sets are used to illustrate the methodologies.

An Econometric Analysis of Hospital Length of Stay for Cataract Operations in Japan by the Box-Cox Transformation Model and Hausman Tests: Evaluation of the 2010 Revision of the Medical Payment System

The Japanese medical costs for cataract treatments reached 270 billion yen in fiscal year 2012. Since the length of stay (LOS) in hospital is much longer than other major countries, controlling the medical costs by reducing LOS becomes an important issue in Japan. In this paper, we evaluated the effects of the 2010 revision of the Japanese medical payment system (DPC/PDPS) on LOS for cataract operations. The Box-Cox transformation model, Nawata’s estimators and Hausman tests were used in the analysis. To evaluate the effects, we analyzed a dataset obtained from 34 DPC hospitals (Hp1-34) where one-eye cataract operations were performed both before (April 2008-March 2010) and after (April 2010-March 2012) the 2010 revision and there were more than 500 patients. The dataset contained information from 32,593 patients. We did not admit the effect of the 2010 revision in this study, and there were large differences LOS among hospitals, even after removing the influences of factors such as patient characteristics and types of principal diseases.

Asymptotic Efficiency of the Maximum Likelihood Estimator for the Box-Cox Transformation Model with Heteroscedastic Disturbances

This paper considers the asymptotic efficiency of the maximum likelihood estimator (MLE) for the Box-Cox transformation model with heteroscedastic disturbances. The MLE under the normality assumption (BC MLE) is a consistent and asymptotically efficient estimator if the “small ” condition is satisfied and the number of parameters is finite. However, the BC MLE cannot be asymptotically efficient and its rate of convergence is slower than ordinal order when the number of parameters goes to infinity. Anew consistent estimator of order is proposed. One important implication of this study is that estimation methods should be carefully chosen when the model contains many parameters in actual empirical studies.

A Neuro-Based Software Fault Prediction with Box-Cox Power Transformation

Software fault prediction is one of the most fundamental but significant management techniques in software dependability assessment. In this paper we concern the software fault prediction using a multilayer-perceptron neural network, where the underlying software fault count data are transformed to the Gaussian data, by means of the well-known Box-Cox power transformation. More specially, we investigate the long-term behavior of software fault counts by the neural network, and perform the multi-stage look ahead prediction of the cumulative number of software faults detected in the future software testing. In numerical examples with two actual software fault data sets, we compare our neural network approach with the existing software reliability growth models based on nonhomogeneous Poisson process, in terms of predictive performance with average relative error, and show that the data transformation employed in this paper leads to an improvement in prediction accuracy.

Improvement of Misclassification Rates of Classifying Objects under Box Cox Transformation and Bootstrap Approach

Discrimination and classification rules are based on different types of assumptions. Also, all most statistical methods are based on some necessary assumptions. Parametric methods are the best choice if it follows all the underlying assumptions. When assumptions are violated, parametric approaches do not provide a better solution and nonparametric techniques are preferred. After Box-Cox transformation, when assumptions are satisfied, parametric methods provide fewer misclassification rates. With this problem in mind, our concern is to compare the classification accuracy of parametric and non-parametric approaches with the aid of Box-Cox transformation and Bootstrapping. We carried Support Vector Machines (SVMs) and different discrimination and classification rules to classify objects. The attention is to critically compare the SVMs with Linear discrimination Analysis (LDA), and Quadratic discrimination Analysis (QDA) for measuring the performance of these techniques before and after Box-Cox transformation using misclassification rates. From the apparent error rates, we observe that before Box-Cox transformation, SVMs perform better than existing classification techniques, on the other hand, after Box-Cox transformation, parametric techniques provide fewer misclassification rates compared to nonparametric method. We also investigated the performances of classification techniques using the Bootstrap approach and observed that Bootstrap-based classification techniques significantly reduce the classification error rate than the usual techniques of small samples. Thus, this paper proposes to apply classification techniques under the Bootstrap approach for classifying objects in case of small sample. A real and simulated datasets application is carried out to see the performance.

基于Box-Cox幂转换模型的非正态过程能力分析

标准过程能力指数是基于过程输出服从正态分布的假设建立的。实际中存在大量不服从正态分布的过程输出,几何公差类质量特性就是其中一种。本文在数据转换方法基础上,基于Box-Cox幂转换模型进行偏态数据正态化来专门处理此类质量特性的过程能力指数计算。通过仿真研究了该方法在过程能力分析中的适用性和效果。仿真结果和案例分析显示,该方法计算简单、结果可靠。

Box-Cox变换下联合均值与方差模型的极大似然估计

在提出Box-Cox变换下联合均值与方差模型的基础上,研究了该模型参数的估计问题。同时利用截面极大似然估计方法对变换参数λ进行估计,并对均值模型和方差模型的参数进行极大似然估计。通过随机模拟和实例研究,结果表明该模型和方法是有效和可行的。

Box-Cox变换原理及其在财务比率正态分布中的作用

对上海深圳交易所1998～2002年1 100余家公司5 571份年报12个财务比率的综合研究揭示,绝大多数财务比率不服从正态分布且不易变换到接近正态.正态变换实证过程表明:原始财务比率数据经行业划分、剔除污染样本后再进行Box-Cox变换的的正态变换效率最高,可使绝大多数财务比率接近正态分布,但仍有少数比率无法正态化.

Johnson转换与Box-Cox转换相比的优越性

非正态数据转换成正态数据的方法有很多,其中两种是使用Box-Cox转换和Johnson转换.本文应用Box-Cox转换和Johnson转换对几种非正态分布进行了研究,并计算出了其过程能力指数,通过大量的重复模拟研究了该方法在过程能力分析中的适用性和效果.结果显示,Johnson转换比Box-Cox转换更有效.

基于Box-Cox变换的住宅特征价格理论研究

在特征价格模型的应用中,函数形式的选择具有多样化,包括线性函数、对数函数、半对数函数等。在国外研究的基础上,提出在线性函数应用的基础上,对模型进行Box-Cox变换,并利用线性Box-Cox特征模型对巴黎的住宅市场进行实证研究。实证研究的结果有效地解释了各个特征与价格之间的关系,同时还说明,对住宅特征的数据变换可以有效地改善模型结构,使得模型的拟合效果更好,从而证实了该特征模型的有效性及优越性。

Box-Cox变换模型模拟矩估计方法研究

基于对Ｂｏｘ－Ｃｏｘ变换模型参数估计方法的研究，分析了极大似然方法之不足，提出了相应参数估计方法——基于残差的广义模拟矩估计方法，并研制了相应的算法．该方法同时解决了Ｂｏｘ－Ｃｏｘ变换模型出现序列相关与异方差时的参数估计问题，力求反映真实模型．

Box-Cox变换的黄金分割法实现

提出可以使用黄金分割法确定 Box- Cox变换中的参数 ,给出了一种计算步骤。提出了通过多搜索几个区间和回归诊断来更大限度地保证所确定出的参数是合用的。并从理论分析和实例检验两方面说明了与一维格点搜索法相比 ,使用黄金分割法确定 Box- Cox变换中的参数计算量较小 ,容易使计算结果达到较高的精确度 ,且易用性也有所提高。

Box-Cox-SV模型及其对金融时间序列刻画能力研究

利用Box-Cox变换构造的随机波动模型,即Box-Cox-SV模型,较好地概括了现有文献中出现的一些常用SV类模型,避免了模型选择中的困难.论证了该类模型的矩属性和平方序列的自相关特征,利用MCMC估计方法对上证指数收益序列建立了Box-Cox-SV模型,并与EGARCH模型对金融时间序列的刻画能力在理论上和实证上进行了对比研究.

Box-Cox变换在构建房地产特征价格模型中的应用

传统房地产价格指数的建立忽略了对商品同质性的要求,特征价格模型可以解决同质性问题,但多样的函数形式下得出的结果也存在一定的差距。因而,文中将Box-Cox变换应用于特征价格指数的建立过程中。在西安市住宅数据信息的基础上,通过Box-Cox变换,选择对数线性函数建立特征价格模型,并以此编制价格指数。研究结果表明,Box-Cox特征价格指数具有相对精确性。

基于Box-Cox变换的风电场短期风速预测模型

风电场准确的风速预测可以减轻或避免风电对电网的不利影响,有利于在开放的电力市场环境下正确制定电能交换计划,提高风电竞争力。基于风速序列的时序性,使用极大似然法对风速序列进行了Box-Cox最优变换,建立了ARMA(p,q)风速预测模型。为检验时间序列模型的有效性,利用最小信息准则中的BIC(Bayesian Information Criterion)函数对ARMA(p,q)模型进行识别,并通过风速频率曲线对预测结果进行了修正。仿真结果和算例验证了该方法在风电场风速预测中的适用性,具有一定的实用价值。

BOX-COX变换与微电路工艺设备表征

(利用部分要因试验设计与数据转换表征微电路工艺设备)。因为试验数据的尺度效应和测量的固有属性,试验数据常违反模型误差的正态和一致性假设。通过BOX-COX数据转换分析,确定热氧化工艺目标值的最优转换形式,针对转换后数据建立的回归模型满足上述假设。结果表明:数据转换的建模方法能满足方差分析的假设(违反度减轻),并且能更多发掘数据信息,氧化膜厚的模型拟合修正判定系数R2由93.54%增加到98.64%。所得模型用于优化工艺条件,在满足膜厚目标下,非均匀性由0.2%减小到0.08%。文中讨论的基于数据转换的建模方法可以用于半导体制造其他工艺。