Thus proposes an alternative method for the research of superiority of two predictors based on the biased estimation . in the light of the approximate multicollinearity of matrix , distance for principal components estimation ( namely distance ) is put forward 针对设计矩阵的多重共线性问题，为了改进基于最小二乘估计的统计诊断量cook距离，提出了基于massy主成分下的cook距离( mpcc距离) 。
The main results are as follows : according to the approximate multicollinearity of matrix , the third chapter constrains the regression coefficient and obtains generalized ridge estimation of the linear model ' s parameter under the ellipsoidal restriction 主要结果如下：论文第三章从设计矩阵的多重共线性角度出发，考虑回归系数的椭球约束，获得了椭球约束下线性模型参数的一种新型估计- -广义岭型估计。
( 2 ) the performance of support vector machine ( svm ) for classification was analyzed . it was found that svm for classification is more sensitive to noise than other methods , in particular , the kernel function , its parameter and penalty factor c are the main factor affecting the classification performance of svm ( 2 )支持向量机采用了结构风险最小化( srm )原则，用于模式分类已表现出优良的性能，但在观测数据中存在复共线性时，其分类效果就有所降低。
The conclusions elicited by so many studies at home and abroad indicated that the financial data and financial index can be used to predict the financial crisis or bankruptcy risk of an enterprise , and in case of the methods in the field of financial risk prediction has inclined to be stability , and no important breakthrough in recent years 国内外许多研究得出的结论已经表明，财务数据和财务指标可用于预测企业的财务危机或破产风险。在财务危机预测领域，就研究方法而言，已经趋于稳定，近几年来始终没有重大的突破，相关的研究只是从技术细节上不断的完备，目前仍然存在着一些问题，如：预测变量的选择、多重共线性等问题，始终没有得到有效的解决。
Strong the relationship of tax and economy , adjust the structure of budgetary expenditure … ) and some points need further research ( e . g . the analysis of tax structure … ) this paper adopt unit root test , cointegration test and ecm model to solve the spurious regression of traditional forecast model . var model has good forecast effect and stepwise regression can solve multicollinearity 本文在继承前辈研究成果的基础上力争有所突破,在研究方法上,针对传统税收预测模型存在的某些缺陷,采用单位根检验、协整检验及ecm模型解决困扰计量经济学界多时的伪回归问题; grange因果关系检验、 var模型被证明具有较好的预测效果;逐步回归则有效的克服了多重共线性带来的问题。
Based on the co - linearity analysis of runoff and precipitation among different hydrological stations and various kinds of water and soil conservation measures , a statistical hydrological model of precipitation - soil and water conservation - runoff for the river basin is established by applying multiple regression method to analyze indicators and runoff data 摘要本文在变量共线性分析基础上，提出了流域降水量标度和水土保持标度及其计算方法，建立了流域降水水土保持径流统计模型，该模型不仅能分离水土保持措施对河川径流量影响程度，而且还可分析降水及水土保持对流域径流量变化的影响。
Then , the default ratios of 45 st - companies are computed and 37 potential financial index are selected referred by researches on financial distress at home and abroad . finally , the equation of default ratio is produced by stepwise regression , and three of the basic problems in linear regression are considered well , that is case - wise diagnostics and auto - correlated errors , as well as collinear relationship and teteroskedastisity 随后，利用该期权定价理论违约率模型计算出45家st公司的违约率，结合国内外有关财务预警研究成果，收集37个相关财务指标，运用逐步回归法，通过剔除异常值、处理自相关、诊断共线性、检验异方差，建立有效回归方程。
The dissertation is divided into six chapters . chapter 1 , summary , which explain the importance of the topic and suggest the system , method , and main contents of this dissertation . chapter 2 : the research of the theory of national debt and the practice of the debts issuing in china , in this part , we sum up the theory of national debts and the method of researching moderate scale in china and other countries . chapter 3 : the analysis of burden of national debts in china , which analyze the debts " burden by the rate of debts " burden and the rate of repayment of debts and the degree dependence of debts and so on . chapter 4 : influence factor study of the reasonable limit of national debts " quantity , in this chapter we get the factors that mostly affect the scale . using the actual datum and modern econometric and statistical analysis method , we conclude that the repayment of capital and interest and the finance deficit are the most important factors 第二章国债理论研究进展和我国的国债实践，综述国内外国债理论研究的进展和我国国债发行的实践以及国债适度规模的研究方法。第三章我国国债债务负担分析，主要从政府偿债能力和社会应债能力两方面，选取了债务依存度、国债负担率和国债偿债率等指标，通过横纵对比，对我国国债债务负担进行了分析。第四章债务负担合理数量界限的影响因素分析，选取了九个与国债密切相关的指标，通过多重共线性诊断、最佳回归模型的选择分析，最后选定国债还本付息额和财政赤字两个与国债规模最密切的指标。
