民生银行小微企业贷款Lasso指标选择及Copula评价
摘要
小微企业是民生银行三大核心客户群体之一，民生银行已经成为全球最大的小微企业金融服务提供商。在“高信用风险、高人工成本”的小微企业贷款业务中，如何降低不良贷款率是小微金融能否持续发展的关键之一。降低不良贷款率的核心在于如何从众多小微企业中甄选出优质客户。本文以客观数据为依据，基于定量分析方法，得到结论，对小微金融的发展提供借鉴和帮助。
根据民生银行TJ分行商贷通申请材料，整理出24个指标。以授信额度为因变量，其它变量为自变量。采用最小角回归、广义线性模型弹性网和分组Lasso三种方法计算。结果发现Lasso变量选择功能最强，弹性网次之，而分组Lasso较弱。综合几种方法结果，企业从事行业对于银行贷款授信额度影响最大，一般建筑、交通运输设备容易获得贷款，而从事金属、日用品的企业较难获得更多贷款。处于事业巅峰期的中年企业家，不管是离异还是没有离异都较易获得更多的银行授信额度，而处于创业期的青年未婚者不太容易从银行获得贷款。
根据Lasso回归分析结果表明，企业从事行业对于小微贷款的影响力最大，这点与民生银行推行的“打造专业化支行”战略不谋而合。比较成功的例子是民生银行QZ分行和FZ分行。在分析传统版小微业务存在的缺陷后，提出提升版小微金融基本特征。从优化业务结构措施、担保细则、小微业务风险对策、内部制度建设、售后管理方法五个方面提出改进小微金融的具体措施和条件。
Copula实际是一个多元分布函数，主要用于独立同分布多元时间序列建模。本文首次将Coupla方法用于综合评价。根据Lasso回归结果分析，最终选择婚姻状况、已有额度、资产合计、从事行业II四个指标作为申请人贷款能力综合评价指标体系。对于每个指标单独拟合一元分布，把累积分布函数看成标准化函数，标准化数值服从[0,1]区间的均匀分布。采用基于经验Copula的拟合优度检验从5种常见的Copula，正态Copula、t Copula、Gumbel Copula、Frank Copula和ClaytonCopula中选择最优的t Copula，极大似然估计其参数。最后将Copula分布函数值当成综合评价值，给出申请人贷款能力排名。排名结果符合实际授信额度。
根据民生银行汇总数据，为了比较各分行存贷效率，选择了存款和贷款指标。以累加DEA模型、自助DEA模型、对偶DEA模型、超效率DEA模型计算各分行效率，各种模型计算结果几乎一致。效率最低的是CC分行，其次是WH分行。TY、JN、TJ、KM、ZZ和NC效率在0.8到0.9之间。ST分行效率接近1，是所有没有达到技术有效分行中效率最高的。最后以SFA计算效率，给出各分行最终排名。
Small and micro businesses is one of the three core customers in Minsheng Bank.Minsheng Bank has become the world’s largest small and micro financial serviceproviders. High credit risk and high labor costs are the main characters in small andmicro business. How to reduce the non-performing loan ratio is the key for sustainabledevelopment. A guarantee is to select high quality customers from numerous applicant.Based on applicant data, conclusion was gained to provide reference and help of to thedevelopment of small and micro finance by quantitative analysis.
24indicators were complied from application materials of Commercial Sense inMinsheng Bank TJ Branch. Credit indicator was taken as the dependent variable andother variables as independent variables. Three algorithms, Least Angle Regression,Elastic Network and Group Lasso were chosen. The results found that Lasso had thestrongest capacity of variable selection, Elastic Network was the middle, and GroupLasso was the weakest. In a whole, enterprises industry had the greatest efect on credit.Industries of general construction and transportation equipment were easy to get loans.Meanwhile, enterprises engaged in metal and daily necessities were difcult to get moreloans.
The Lasso regression showed that engaged industry of small and micro enterpriseshas the greatest influence for loan. It happened to have the same view with the strategyof”building professional branch” in Minsheng Bank. Successful examples were FZbranch and QZ branch. The imperfection of traditional small and micro business wasanalyzed and upgrading version characteristics were put forward. Details of structureoptimization measures, guarantee conditions, small and micro business risk counter-measure, internal system construction and after-sales management came up to improvesmall and micro finance.
Copulas is actually a multivariate distribution function. It is mainly used for mul-tivariate time series modeling of independent identically distributed case. We originallyused Coupla as comprehensive evaluation. According to the experience, four indica-tors, marital status, existing lines, total assets and engaged industry were chosen asevaluation indexes system for loan applicant ability. Each index’s distribution was fit-ted separately and the cumulative distribution function was taken as standardization. Standardized value obeyed uniform distribution of [0,1] interval. Based on a goodness-of-fit test from experience copula, five copula, Normal Copula, t Copula, Gumbel Cop-ula, Frank Copulas and Clayton Copula, were taken as candidates and the optimum tCopula was t Copula. Parameters was estimated by.Maximum likelihood Estimates.Finally Copula distribution function was taken as evaluation value which gave capacityranking of applicant lending. The order conformed to the actual credit ranking results.
According to Minsheng bank summary data, saving and loan indicators were se-lected for efciency evaluation. Accumulate DEA, Bootstrap DEA, Dual DEA, SuperDEA were applied to calculate efciencies of each branch. The results of four modelwere almost the same. CG branch had the lowest efciency. and WH branch followed.The efciencies of TY, KM, JN, TJ, ZZ and NC branches distributed between0.8and0.9. ST branch’s efciency was close to one and had the highest efcient in all thetechnical inefciencies. Finally the ranking of each branch was computed by SFA.
根据民生银行TJ分行商贷通申请材料，整理出24个指标。以授信额度为因变量，其它变量为自变量。采用最小角回归、广义线性模型弹性网和分组Lasso三种方法计算。结果发现Lasso变量选择功能最强，弹性网次之，而分组Lasso较弱。综合几种方法结果，企业从事行业对于银行贷款授信额度影响最大，一般建筑、交通运输设备容易获得贷款，而从事金属、日用品的企业较难获得更多贷款。处于事业巅峰期的中年企业家，不管是离异还是没有离异都较易获得更多的银行授信额度，而处于创业期的青年未婚者不太容易从银行获得贷款。
根据Lasso回归分析结果表明，企业从事行业对于小微贷款的影响力最大，这点与民生银行推行的“打造专业化支行”战略不谋而合。比较成功的例子是民生银行QZ分行和FZ分行。在分析传统版小微业务存在的缺陷后，提出提升版小微金融基本特征。从优化业务结构措施、担保细则、小微业务风险对策、内部制度建设、售后管理方法五个方面提出改进小微金融的具体措施和条件。
Copula实际是一个多元分布函数，主要用于独立同分布多元时间序列建模。本文首次将Coupla方法用于综合评价。根据Lasso回归结果分析，最终选择婚姻状况、已有额度、资产合计、从事行业II四个指标作为申请人贷款能力综合评价指标体系。对于每个指标单独拟合一元分布，把累积分布函数看成标准化函数，标准化数值服从[0,1]区间的均匀分布。采用基于经验Copula的拟合优度检验从5种常见的Copula，正态Copula、t Copula、Gumbel Copula、Frank Copula和ClaytonCopula中选择最优的t Copula，极大似然估计其参数。最后将Copula分布函数值当成综合评价值，给出申请人贷款能力排名。排名结果符合实际授信额度。
根据民生银行汇总数据，为了比较各分行存贷效率，选择了存款和贷款指标。以累加DEA模型、自助DEA模型、对偶DEA模型、超效率DEA模型计算各分行效率，各种模型计算结果几乎一致。效率最低的是CC分行，其次是WH分行。TY、JN、TJ、KM、ZZ和NC效率在0.8到0.9之间。ST分行效率接近1，是所有没有达到技术有效分行中效率最高的。最后以SFA计算效率，给出各分行最终排名。
Small and micro businesses is one of the three core customers in Minsheng Bank.Minsheng Bank has become the world’s largest small and micro financial serviceproviders. High credit risk and high labor costs are the main characters in small andmicro business. How to reduce the non-performing loan ratio is the key for sustainabledevelopment. A guarantee is to select high quality customers from numerous applicant.Based on applicant data, conclusion was gained to provide reference and help of to thedevelopment of small and micro finance by quantitative analysis.
24indicators were complied from application materials of Commercial Sense inMinsheng Bank TJ Branch. Credit indicator was taken as the dependent variable andother variables as independent variables. Three algorithms, Least Angle Regression,Elastic Network and Group Lasso were chosen. The results found that Lasso had thestrongest capacity of variable selection, Elastic Network was the middle, and GroupLasso was the weakest. In a whole, enterprises industry had the greatest efect on credit.Industries of general construction and transportation equipment were easy to get loans.Meanwhile, enterprises engaged in metal and daily necessities were difcult to get moreloans.
The Lasso regression showed that engaged industry of small and micro enterpriseshas the greatest influence for loan. It happened to have the same view with the strategyof”building professional branch” in Minsheng Bank. Successful examples were FZbranch and QZ branch. The imperfection of traditional small and micro business wasanalyzed and upgrading version characteristics were put forward. Details of structureoptimization measures, guarantee conditions, small and micro business risk counter-measure, internal system construction and after-sales management came up to improvesmall and micro finance.
Copulas is actually a multivariate distribution function. It is mainly used for mul-tivariate time series modeling of independent identically distributed case. We originallyused Coupla as comprehensive evaluation. According to the experience, four indica-tors, marital status, existing lines, total assets and engaged industry were chosen asevaluation indexes system for loan applicant ability. Each index’s distribution was fit-ted separately and the cumulative distribution function was taken as standardization. Standardized value obeyed uniform distribution of [0,1] interval. Based on a goodness-of-fit test from experience copula, five copula, Normal Copula, t Copula, Gumbel Cop-ula, Frank Copulas and Clayton Copula, were taken as candidates and the optimum tCopula was t Copula. Parameters was estimated by.Maximum likelihood Estimates.Finally Copula distribution function was taken as evaluation value which gave capacityranking of applicant lending. The order conformed to the actual credit ranking results.
According to Minsheng bank summary data, saving and loan indicators were se-lected for efciency evaluation. Accumulate DEA, Bootstrap DEA, Dual DEA, SuperDEA were applied to calculate efciencies of each branch. The results of four modelwere almost the same. CG branch had the lowest efciency. and WH branch followed.The efciencies of TY, KM, JN, TJ, ZZ and NC branches distributed between0.8and0.9. ST branch’s efciency was close to one and had the highest efcient in all thetechnical inefciencies. Finally the ranking of each branch was computed by SFA.
引文
[1] Tibshirani R. Regression shrinkage and selection via the lasso[J]. Journal of theRoyal Statistical Society. Series B (Methodological),1996,58(1):267–288.
[2] Breiman L. Better subset regression using the nonnegative garrote[J]. Techno-metrics,1995,37(4):373–384.
[3] Tibshirani R, et al. The lasso method for variable selection in the Cox model[J].Statistics in medicine,1997,16(4):385–395.
[4] Efron B, Hastie T, Johnstone I, et al. Least angle regression[J]. The Annals ofstatistics,2004,32(2):407–499.
[5] Zou H, Hastie T. Regularization and variable selection via the elastic net[J]. Jour-nal of the Royal Statistical Society: Series B (Statistical Methodology),2005,67(2):301–320.
[6] Fan J, Li R. Variable selection via nonconcave penalized likelihood and itsoracle properties[J]. Journal of the American Statistical Association,2001,96(456):1348–1360.
[7] Zou H. The adaptive lasso and its oracle properties[J]. Journal of the AmericanStatistical Association,2006,101(476):1418–1429.
[8] Tibshirani R, Saunders M, Rosset S, et al. Sparsity and smoothness via the fusedlasso[J]. Journal of the Royal Statistical Society: Series B (Statistical Methodol-ogy),2004,67(1):91–108.
[9] Meinshausen N. Relaxed lasso[J]. Computational Statistics&Data Analysis,2007,52(1):374–393.
[10] Meier L, Van De Geer S, Bu¨hlmann P. The group lasso for logistic regres-sion[J]. Journal of the Royal Statistical Society: Series B (Statistical Method-ology),2008,70(1):53–71.
[11] Friedman J, Hastie T, Tibshirani R. A note on the group lasso and a sparse grouplasso[J]. arXiv preprint arXiv:1001.0736,2010.
[12] Park T, Casella G. The bayesian lasso[J]. Journal of the American StatisticalAssociation,2008,103(482):681–686.
[13] Zhao P, Yu B. Boosted lasso[R]. Washington: DTIC Document,2004.
[14] Gao J, Kwan P W, Shi D. Sparse kernel learning with LASSO and Bayesianinference algorithm[J]. Neural Networks,2010,23(2):257–264.
[15] Shiraishi Y, Fukumizu K. Statistical approaches to combining binary classifiersfor multi-class classification[J]. Neurocomputing,2011,74(5):680–688.
[16] Friedman J, Hastie T, Tibshirani R. Regularization paths for generalized linearmodels via coordinate descent[J]. Journal of statistical software,2010,33(1):1–22.
[17] Kim J, Kim Y, Kim Y. A gradient-based optimization algorithm for LASSO[J].Journal of Computational and Graphical Statistics,2008,17(4):994–1009.
[18] Park M Y, Hastie T. L1-regularization path algorithm for generalized linear mod-els[J]. Journal of the Royal Statistical Society: Series B (Statistical Methodol-ogy),2007,69(4):659–677.
[19] Osborne M R, Presnell B, Turlach B A. On the lasso and its dual[J]. Journal ofComputational and Graphical statistics,2000,9(2):319–337.
[20] Keerthi S S, Shevade S. A fast tracking algorithm for generalized LARS/LASSO[J]. IEEE Transactions on Neural Networks,2007,18(6):1826–1830.
[21] Wu T T, Lange K. Coordinate descent algorithms for lasso penalized regres-sion[J]. The Annals of Applied Statistics,2008,2(1):224–244.
[22] Li R, Wu B. Sparse regularized discriminant analysis with application to mi-croarrays[J]. Computational Biology and Chemistry,2012,39(8):14–19.
[23] Huang T, Gong H, Yang C, et al. ProteinLasso: A Lasso regression approach toprotein inference problem in shotgun proteomics[J]. Computational Biology andChemistry,2013,43(4):46–54.
[24] Cribben I, Haraldsdottir R, Atlas L Y, et al. Dynamic connectivity regression:Determining state-related changes in brain connectivity[J]. NeuroImage,2012,61(4):907–920.
[25] Tomioka R, Merller K R. A regularized discriminative framework for EEG analy-sis with application to brain computer interface[J]. NeuroImage,2010,49(1):415–432.
[26] Mu Y. Computational facial attractiveness prediction by aesthetics-aware fea-tures[J]. Neurocomputing,2013,99(1):59–64.
[27] Ryali S, Chen T, Supekar K, et al. Estimation of functional connectivity infMRI data using stability selection-based sparse partial correlation with elasticnet penalty[J]. NeuroImage,2012,59(4):3852–3861.
[28] Meinshausen N, Bu¨hlmann P. High-dimensional graphs and variable selectionwith the lasso[J]. The Annals of Statistics,2006,34(3):1436–1462.
[29] Friedman J, Hastie T, Tibshirani R. Sparse inverse covariance estimation withthe graphical lasso[J]. Biostatistics,2008,9(3):432–441.
[30] Friedman J, Hastie T, Tibshirani R. Applications of the lasso and grouped lassoto the estimation of sparse graphical models[R]. Standford: Technical report,Stanford University,2010.
[31] Yuan M, Lin Y. Model selection and estimation in the Gaussian graphicalmodel[J]. Biometrika,2007,94(1):19–35.
[32] Mazumder R, Hastie T. The graphical lasso: New insights and alternatives[J].arXiv preprint arXiv:1111.5479,2011.
[33] Wang H. Structured sparse linear graph embedding[J]. Neural Networks,2012,27(3):38–44.
[34] Nelsen R B. An introduction to copulas[M]. Berlin: Springer Verlag,1999.
[35] Embrechts P, Lindskog F, McNeil A. Modelling dependence with copulas andapplications to risk management[J]. Handbook of heavy tailed distributions infinance,2003,8(1):329–384.
[36] Nikoloulopoulos A K, Joe H, Li H. Vine copulas with asymmetric tail depen-dence and applications to financial return data[J]. Computational Statistics&Data Analysis,2012,56(11):3659–3673.
[37] Genest C, Nesˇlehova′J, Quessy J F. Tests of symmetry for bivariate copulas[J].Annals of the Institute of Statistical Mathematics,2012,64(4):811–834.
[38] Zimmer D M. The role of copulas in the housing crisis[J]. Review of Economicsand Statistics,2012,94(2):607–620.
[39] Piani C, Haerter J. Two dimensional bias correction of temperature and pre-cipitation copulas in climate models[J]. Geophysical Research Letters,2012,39(20):71–82.
[40] Fermanian J D. An overview of the goodness-of-fit test problem for copulas[H].2012.
[41] Chen Z, Osadetz K G, Dixon J, et al. Using copulas for implementation of vari-able dependencies in petroleum resource assessment: Example from Beaufort-Mackenzie Basin, Canada[J]. AAPG bulletin,2012,96(3):439–457.
[42] Emrouznejad A, Parker B R, Tavares G. Evaluation of research in efciency andproductivity: A survey and analysis of the first30years of scholarly literature inDEA[J]. Socio-economic planning sciences,2008,42(3):151–157.
[43] Cooper W W, Seiford L M, Zhu J. Data envelopment analysis: History, models,and interpretations[J]. Inernational Series in Operations Research and Manage-ment Science,2011,164:1–39.
[44] Cooper W W, Seiford L M, Zhu J. Handbook on data envelopment analysis[M].Berlin: Springer,2011.
[45] Johnson A L, Kuosmanen T. One-stage and two-stage DEA estimation of theefects of contextual variables[J]. European Journal of Operational Research,2012,220(2):559–570.
[46] Lewis H F, Mallikarjun S, Sexton T R. Unoriented Two-Stage DEA: The Caseof the Oscillating Intermediate Products[J]. European Journal of OperationalResearch,2013,229(2):529–539.
[47] Friesner D, Mittelhammer R, Rosenman R. Inferring the incidence of industryinefciency from DEA estimates[J]. European Journal of Operational Research,2013,224(2):414–424.
[48] Paradi J C, Zhu H, Edelstein B. Identifying managerial groups in a large Cana-dian bank branch network with a DEA approach[J]. European Journal of Opera-tional Research,2012,219(1):178–187.
[49] Yang F, Ang S, Xia Q, et al. Ranking DMUs by using interval DEA cross ef-ficiency matrix with acceptability analysis[J]. European Journal of OperationalResearch,2012,223(2):483–488.
[50] Lee H S, Zhu J. Super-efciency infeasibility and zero data in DEA[J]. EuropeanJournal of Operational Research,2012,216(2):429–433.
[51] Fang L. A generalized DEA model for centralized resource allocation[J]. Euro-pean Journal of Operational Research,2013,228(2):405–412.
[52] R-dder W, Reucher E. Advanced X-efciencies for CCR-and BCC-models?towards Peer-based DEA controlling[J]. European Journal of Opera-tional Research,2012,219(2):467–476.
[53] Lozano S. Information sharing in DEA: A cooperative game theory approach[J].European Journal of Operational Research,2012,222(3):558–565.
[54] Krivonozhko V E, Frrsund F R, Lychev A V. A note on imposing strong com-plementary slackness conditions in DEA[J]. European Journal of OperationalResearch,2012,220(3):716–721.
[55] Sarkis J, Cordeiro J J. Ecological modernization in the electrical utility indus-try: An application of a bads-goods DEA model of ecological and technical ef-ciency[J]. European Journal of Operational Research,2012,219(2):386–395.
[56] Washio S, Yamada S, Tanaka T, et al. Improvements by analyzing the efcientfrontier in DEA[J]. European Journal of Operational Research,2012,217(1):173–184.
[57] Falagario M, Sciancalepore F, Costantino N, et al. Using a DEA-cross efciencyapproach in public procurement tenders[J]. European Journal of OperationalResearch,2012,218(2):523–529.
[58] Ouellette P, Quesnel J P, Vigeant S. Measuring returns to scale in DEA modelswhen the firm is regulated[J]. European Journal of Operational Research,2012,220(2):571–576.
[59] Vaninsky A. Prospective national and regional environmental performance:Boundary estimations using a combined data envelopment?stochastic frontieranalysis approach[J]. Energy,2010,35(9):3657–3665.
[60] Azadeh A, Asadzadeh S, Saberi M, et al. A Neuro-fuzzy-stochastic frontier anal-ysis approach for long-term natural gas consumption forecasting and behavioranalysis: The cases of Bahrain, Saudi Arabia, Syria, and UAE[J]. Applied En-ergy,2011,88(11):3850–3859.
[61] Mastromarco C, Ghosh S. Foreign Capital, Human Capital, and Efciency: AStochastic Frontier Analysis for Developing Countries[J]. World Development,2009,37(2):489–502.
[62] Manlagit M C V. Cost efciency, determinants, and risk preferences in banking:A case of stochastic frontier analysis in the Philippines[J]. Journal of AsianEconomics,2011,22(1):23–35.
[63] Holmgren J. The efciency of public transport operations? An evaluation us-ing stochastic frontier analysis[J]. Research in Transportation Economics,2013,39(1):50–57.
[64] Wang M, Wong M C S. International R&D Transfer and Technical Ef-ciency: Evidence from Panel Study Using Stochastic Frontier Analysis[J]. WorldDevelopment,2012,40(10):1982–1998.
[65] Scotti D, Malighetti P, Martini G, et al. The impact of airport competition ontechnical efciency: A stochastic frontier analysis applied to Italian airport[J].Journal of Air Transport Management,2012,22(7):9–15.
[66] Carree M A. Technological inefciency and the skewness of the error componentin stochastic frontier analysis[J]. Economics Letters,2002,77(1):101–107.
[67] Wu Y. The productive efciency of Chinese iron and steel firms A stochasticfrontier analysis[J]. Resources Policy,1995,21(3):215–222.
[68] Kraft E, Trtrolu D. Bank Efciency in Croatia: A Stochastic-Frontier Analy-sis[J]. Journal of Comparative Economics,1998,26(2):282–300.
[69] yuan Dong X, Putterman L. Productivity and Organization in China’s Rural In-dustries: A Stochastic Frontier Analysis[J]. Journal of Comparative Economics,1997,24(2):181–201.
[70] Niquidet K, Nelson H. Sawmill production in the interior of British Columbia:A stochastic ray frontier approach[J]. Journal of Forest Economics,2010,16(4):257–267.
[71] Helvoigt T L, Adams D M. A stochastic frontier analysis of technical progress,efciency change and productivity growth in the Pacific Northwest sawmill in-dustry[J]. Forest Policy and Economics,2009,11(4):280–287.
[72] Yang H H. Measuring the efciencies of Asia-pacific international airports-Parametric and non-parametric evidence[J]. Computers&Industrial Engineer-ing,2010,59(4):697–702.
[73] Cullinane K, Wang T F, Song D W, et al. The technical efciency of containerports: Comparing data envelopment analysis and stochastic frontier analysis[J].Transportation Research Part A: Policy and Practice,2006,40(4):354–374.
[74] Lim J, Nam C, Kim S, et al. Forecasting3G mobile subscription in China:A study based on stochastic frontier analysis and a Bass difusion model[J].Telecommunications Policy,2012,36(10):858–871.
[75] Fenn P, Vencappa D, Diacon S, et al. Market structure and the efciency of Euro-pean insurance companies: A stochastic frontier analysis[J]. Journal of Banking&Finance,2008,32(1):86–100.
[76]王占锋,吴耀华,赵林城.删失回归模型中一个LASSO型变量选择和估计方法(英文)[J].应用概率统计,2010(01):66–80.
[77]邵伟,祝丽萍,刘福国,等.对称阵稀疏主成分分析及其在充分降维问题中的应用[J].山东大学学报(理学版),2012(04):116–120+126.
[78]张靖,胡学钢,张玉红,等. K-split Lasso:有效的肿瘤特征基因选择方法[J].计算机科学与探索,2012(12):1136–1143.
[79]马文浩.各种Lq惩罚在变量选择中的应用及其比较[D].济南:山东大学,2012.
[80]谭理想.双线性时间序列模型的Lasso方法定阶[D].南京:南京大学,2012.
[81]梁斌,陈敏,缪柏其,等.基于LARS-Lasso的指数跟踪及其在股指期货套利策略中的应用[J].数理统计与管理,2011(06):1104–1113.
[82]王锋.基于稀疏偏最小二乘算法的生物组学数据融合算法研究[D].长春:吉林大学,2012.
[83]王娉.几种罚似然估计在广义线性模型下的性质[D].重庆:西北大学,2012.
[84]王拓.基因调控网络的线性回归模型及其鲁棒性分析[D].西安:西安电子科技大学,2012.
[85]阎春雨.广义线性模型中纠偏估计的再回归方法[D].济南:山东大学,2012.
[86]冉杨.基于Lasso极限最小学习机和LAB颜色空间的人脸识别研究[D].上海:复旦大学,2012.
[87]柯郑林. Lasso及其相关方法在多元线性回归模型中的应用[D].北京:北京交通大学,2011.
[88]孙丽丽.工具变量回归模型中的变量选择[D].长春:东北师范大学,2008.
[89]赵婷婷. AR（p）模型的Lasso方法定阶[D].长春:东北师范大学,2008.
[90]刘睿智,杜溦.基于LASSO变量选择方法的投资组合及实证分析[J].经济问题,2012(09):103–107.
[91]曲婷,王静.基于Lasso方法的平衡纵向数据模型变量选择[J].黑龙江大学自然科学学报,2012(06):715–722+726.
[92]王大荣,张忠占.线性回归模型中变量选择方法综述[J].数理统计与管理,2010(04):615–627.
[93]梁宝娟,巨永锋,张菁. MKLasso模型的算法与模型选择[J].长安大学学报(自然科学版),2012(04):105–110.
[94]施万锋,胡学钢,俞奎.一种面向高维数据的均分式Lasso特征选择方法[J].计算机工程与应用,2012(01):157–161.
[95]闫丽娜,覃婷,王彤. LASSO方法在Cox回归模型中的应用[J].中国卫生统计,2012(01):58–60+64.
[96]李平,曲博,黄光东.基于Fre′chet Copula的欧式脆弱期权定价[J].管理科学学报,2012,15(4):23–30.
[97]周孝华,张保帅,董耀武.基于Copula-SV-GPD模型的投资组合风险度量[J].管理科学学报,2012,15(12):70–78.
[98]刘喆,陶凤和,贾长治.基于Copula函数的部件相关串联机械系统可靠性分析[J].中国测试,2013,1:031.
[99]赵继超,袁越,傅质馨,等.基于Copula理论的风光互补发电系统可靠性评估[J].电力自动化设备,2013,1:027.
[100]向中华,易文德,曾胜.基于Copula函数我国林业经济发展与气候之间的关系研究[J].林业经济,2012(2):24–27.
[101]李怀宇.基于Copula和SFA的海岸带生态经济非线性研究[D].天津:天津大学,2010.
[102]王宗润,汪武超,王小丁,等.基于条件概率积分变换的多元Copula函数选择[J].管理工程学报,2012,26(3):102–108.
[103]程晓娟.资源、环境两维视角下区域生态效率DEA评价[J].当代经济管理,2013(02):63–68.
[104]未小刚.基于DEA-Malmquist指数的我国体育用品上市公司经营效率研究[J].西安体育学院学报,2013(02).
[105]肖林兴.中国全要素生产率的估计与分解―――ＤＥＡ－Ｍａｌｍｑｕｉｓｔ方法适用性研究及应用[J].贵州财经学院学报,2013(01).
[106]周方涛.基于AHP-DEA方法的区域科技创业人才生态系统评价研究[J].管理工程学报,2013(01):8–14.
[107]刘新慧,陈锦燕,周欢.流动注射法与分光光度法对环境水体中挥发酚测定的比较研究[J].现代仪器,2012(02):59–61.
[108]罗俊浩,崔娥英,季建华.基于随机前沿分析(SFA)的港口上市公司的效率评价[J].武汉理工大学学报(交通科学与工程版),2012(04):736–739.
[109]马跃如,白勇,程伟波.基于SFA的我国文化产业效率及影响因素分析[J].统计与决策,2012(08):97–101.
[110]王博文,韩先锋,卫伟.基于SFA和DEA的中国低碳企业生产效率的比较[J].统计与决策,2012(02):140–142.
[111]徐辉,李健,钟惠波.银行效率与不良贷款冲击效应的实证研究――基于SFA测度分析的应用[J].金融评论,2012(03):29–40+123–124.
[112]周末,王良举,陈甬军.中国钢铁企业的规模过小了吗?――基于NEIO和SFA方法的比较分析[J].产业经济评论,2012(01):1–17.
[113]朱承亮,师萍,安立仁.人力资本及其结构与研发创新效率――基于SFA模型的检验[J].管理工程学报,2012(04):58–64.
[114]陈春,肖光恩,陈林, et al.基于DEA的中国技术效率地区差异估算[J].武汉科技大学学报(社会科学版),2013(01):87–88–89–90.
[115]栾文敬,孙欢,宋媛媛,等.农村养老保险覆盖面投入产出效率评估与影响因素分析――基于DEA与Tobit两步法[J].华中农业大学学报(社会科学版),2013(01):84–89.
[116]刘军.运用SFA方法对我国商业银行支农金融效率的研究[D].合肥:安徽大学,2012.
[117]王丽丽.基于SFA模型的我国东部沿海各省科技创新能力研究[D].青岛:青岛理工大学,2012.
[118]张慧娟.基于SFA方法的徽商银行X-效率测度及影响因素分析[D].南京:南京大学,2012.
[119]王彦霞.秦皇岛:燕山大学,2011.
[120]王顺久,杨志峰,丁晶.关中平原地下水资源承载力综合评价的投影寻踪方法[J].资源科学,2004,26(6):104–110.
[121]杨晓华,杨志峰,郦建强.水质综合评价的遗传投影寻踪插值模型[J].环境工程,2004,22(3):69–71.
[122]严光财,方新安,马朝霞.以神经网络建立武汉地区医院建筑节能综合评价体系[J].数理医药学杂志,2005,18(1):85–86.
[123]李文博,郑文哲.基于神经网络的企业技术创新能力综合评价研究[J].科技进步与对策,2005,22(1):55–57.
[124]孟文清,石华旺,李万庆.基于人工神经网络的建筑工程质量模糊综合评[J].工程建设与设计,2004(12):67–69.
[125]刘锡健,周娟,张恒.关于石油工程项目社会效益的定量化综合评价[J].科技进步与对策,2004,21(12):141–142.
[126]肖健华.基于核方法的智能综合评价框架系统建造方法[J].宝鸡文理学院学报：自然科学版,2003,23(1):8–11,25.
[127]肖健华,吴今培.基于SVM的综合评价方法研究[J].计算机工程,2002,28(8):28–30.
[128]李栋,王洪礼,李胜朋.综合评价法的统一化研究[J].天津大学学报(社会科学版),2006,8(5):373–375.
[129]邱东.多指标综合评价方法的系统分析[M].北京:中国统计出版社,1992.
[130] Friedman J H, Stuetzle W. Projection pursuit regression[J]. J. Amer. Statist.Assoc.,1981,76:817–823.
[131] Fredman J. Multivariate adaptive regression splines(with discussion)[J]. Theannals of statistics,1991,19:1–141.
[132] Vapnik V. The Nature of Statistical Learning Theory[M]. New York: Springer,1995.
[133] Nelsen R. An Introduction to Copulas[M]. Berlin: Springer,1998.
[134]史道济,姚庆祝.改进Copula对数据拟合的方法[J].系统工程理论与实践,2004,24(4):49–55.
[135] Wang W, Wells M T. Model selection and semiparametric inference for bivari-ate failure-time data[J]. Journal of The American Statistical Association,2000,95:62–72.
[136] Fermanian J. Goodness of fit tests for copulas[J]. Journal of Multivariate Anal-ysis,2005,95:119–152.
[137] Cornelia S, Mark T. Goodness-of-fit Tests for Parametric Families ofArchimedean Copulas[R]. Münster: University of Muenster,2004.
[138] Bickel P, Rosenblatt M. On some global meansures of the deviation of densityfunction estimates[J]. Annals of Statistics,1973,1:1071–1095.
[139] Kojadinovic I, Yan J. Modeling Multivariate Distributions with ContinuousMargins Using the copula R Package[J]. Journal of Statistical Software,2010,34(9):1:20.
[140] Berg D. Copula Goodness-of-Git Testing: An Overview and Power Compari-son[J]. The European Journal of Finance,2009,15:675–701.
[141] Genest C, Remillard B, Beaudoin D. Goodness-of-fit tests for copulas: A reviewand a power study[J]. Insurance: Mathematics and Economics,2009,44:199–214.
[142] Genest C R, emillard B. Validity of the Parametric Bootstrap for Goodness-of-Fit Testing in Semiparametric Models. e Probabilit[J]. Annales de lInstitut HenriPoincar e Probabilit es et Statistiques,2008,44:1096–1127.
[143] Kojadinovic I, Yan J. A goodness-of-fit test for multivariate multiparameter cop-ulas based on multiplier central limit theorems[J]. Statistics and Computing,2011,21:17–30.10.1007/s11222-009-9142-y.
[144] Charnes C W, A., E. R. Measuring the inefciency of decision making units[J].European Journal of Operational Research,1978,2:429–444.
[145] Simar L, Wilson P. Statistical inference in nonparametric frontier models: Thestate of the art[J]. Journal of Productivity Analysis,2000,13:49–78.
[146] Cazals J F, C., Simar L. Nonparametric frontier estimation: A robust approach[J].Journal of Econometrics,2002,106:1–25.
[147] Fare R, Grosskopf S, Lindgren B, et al. Productivity changes in Swedish phar-macies1980–1989: A non-parametric Malmquist approach[J]. Journal of Pro-ductivity Analysis,1992,3:85–101.
[2] Breiman L. Better subset regression using the nonnegative garrote[J]. Techno-metrics,1995,37(4):373–384.
[3] Tibshirani R, et al. The lasso method for variable selection in the Cox model[J].Statistics in medicine,1997,16(4):385–395.
[4] Efron B, Hastie T, Johnstone I, et al. Least angle regression[J]. The Annals ofstatistics,2004,32(2):407–499.
[5] Zou H, Hastie T. Regularization and variable selection via the elastic net[J]. Jour-nal of the Royal Statistical Society: Series B (Statistical Methodology),2005,67(2):301–320.
[6] Fan J, Li R. Variable selection via nonconcave penalized likelihood and itsoracle properties[J]. Journal of the American Statistical Association,2001,96(456):1348–1360.
[7] Zou H. The adaptive lasso and its oracle properties[J]. Journal of the AmericanStatistical Association,2006,101(476):1418–1429.
[8] Tibshirani R, Saunders M, Rosset S, et al. Sparsity and smoothness via the fusedlasso[J]. Journal of the Royal Statistical Society: Series B (Statistical Methodol-ogy),2004,67(1):91–108.
[9] Meinshausen N. Relaxed lasso[J]. Computational Statistics&Data Analysis,2007,52(1):374–393.
[10] Meier L, Van De Geer S, Bu¨hlmann P. The group lasso for logistic regres-sion[J]. Journal of the Royal Statistical Society: Series B (Statistical Method-ology),2008,70(1):53–71.
[11] Friedman J, Hastie T, Tibshirani R. A note on the group lasso and a sparse grouplasso[J]. arXiv preprint arXiv:1001.0736,2010.
[12] Park T, Casella G. The bayesian lasso[J]. Journal of the American StatisticalAssociation,2008,103(482):681–686.
[13] Zhao P, Yu B. Boosted lasso[R]. Washington: DTIC Document,2004.
[14] Gao J, Kwan P W, Shi D. Sparse kernel learning with LASSO and Bayesianinference algorithm[J]. Neural Networks,2010,23(2):257–264.
[15] Shiraishi Y, Fukumizu K. Statistical approaches to combining binary classifiersfor multi-class classification[J]. Neurocomputing,2011,74(5):680–688.
[16] Friedman J, Hastie T, Tibshirani R. Regularization paths for generalized linearmodels via coordinate descent[J]. Journal of statistical software,2010,33(1):1–22.
[17] Kim J, Kim Y, Kim Y. A gradient-based optimization algorithm for LASSO[J].Journal of Computational and Graphical Statistics,2008,17(4):994–1009.
[18] Park M Y, Hastie T. L1-regularization path algorithm for generalized linear mod-els[J]. Journal of the Royal Statistical Society: Series B (Statistical Methodol-ogy),2007,69(4):659–677.
[19] Osborne M R, Presnell B, Turlach B A. On the lasso and its dual[J]. Journal ofComputational and Graphical statistics,2000,9(2):319–337.
[20] Keerthi S S, Shevade S. A fast tracking algorithm for generalized LARS/LASSO[J]. IEEE Transactions on Neural Networks,2007,18(6):1826–1830.
[21] Wu T T, Lange K. Coordinate descent algorithms for lasso penalized regres-sion[J]. The Annals of Applied Statistics,2008,2(1):224–244.
[22] Li R, Wu B. Sparse regularized discriminant analysis with application to mi-croarrays[J]. Computational Biology and Chemistry,2012,39(8):14–19.
[23] Huang T, Gong H, Yang C, et al. ProteinLasso: A Lasso regression approach toprotein inference problem in shotgun proteomics[J]. Computational Biology andChemistry,2013,43(4):46–54.
[24] Cribben I, Haraldsdottir R, Atlas L Y, et al. Dynamic connectivity regression:Determining state-related changes in brain connectivity[J]. NeuroImage,2012,61(4):907–920.
[25] Tomioka R, Merller K R. A regularized discriminative framework for EEG analy-sis with application to brain computer interface[J]. NeuroImage,2010,49(1):415–432.
[26] Mu Y. Computational facial attractiveness prediction by aesthetics-aware fea-tures[J]. Neurocomputing,2013,99(1):59–64.
[27] Ryali S, Chen T, Supekar K, et al. Estimation of functional connectivity infMRI data using stability selection-based sparse partial correlation with elasticnet penalty[J]. NeuroImage,2012,59(4):3852–3861.
[28] Meinshausen N, Bu¨hlmann P. High-dimensional graphs and variable selectionwith the lasso[J]. The Annals of Statistics,2006,34(3):1436–1462.
[29] Friedman J, Hastie T, Tibshirani R. Sparse inverse covariance estimation withthe graphical lasso[J]. Biostatistics,2008,9(3):432–441.
[30] Friedman J, Hastie T, Tibshirani R. Applications of the lasso and grouped lassoto the estimation of sparse graphical models[R]. Standford: Technical report,Stanford University,2010.
[31] Yuan M, Lin Y. Model selection and estimation in the Gaussian graphicalmodel[J]. Biometrika,2007,94(1):19–35.
[32] Mazumder R, Hastie T. The graphical lasso: New insights and alternatives[J].arXiv preprint arXiv:1111.5479,2011.
[33] Wang H. Structured sparse linear graph embedding[J]. Neural Networks,2012,27(3):38–44.
[34] Nelsen R B. An introduction to copulas[M]. Berlin: Springer Verlag,1999.
[35] Embrechts P, Lindskog F, McNeil A. Modelling dependence with copulas andapplications to risk management[J]. Handbook of heavy tailed distributions infinance,2003,8(1):329–384.
[36] Nikoloulopoulos A K, Joe H, Li H. Vine copulas with asymmetric tail depen-dence and applications to financial return data[J]. Computational Statistics&Data Analysis,2012,56(11):3659–3673.
[37] Genest C, Nesˇlehova′J, Quessy J F. Tests of symmetry for bivariate copulas[J].Annals of the Institute of Statistical Mathematics,2012,64(4):811–834.
[38] Zimmer D M. The role of copulas in the housing crisis[J]. Review of Economicsand Statistics,2012,94(2):607–620.
[39] Piani C, Haerter J. Two dimensional bias correction of temperature and pre-cipitation copulas in climate models[J]. Geophysical Research Letters,2012,39(20):71–82.
[40] Fermanian J D. An overview of the goodness-of-fit test problem for copulas[H].2012.
[41] Chen Z, Osadetz K G, Dixon J, et al. Using copulas for implementation of vari-able dependencies in petroleum resource assessment: Example from Beaufort-Mackenzie Basin, Canada[J]. AAPG bulletin,2012,96(3):439–457.
[42] Emrouznejad A, Parker B R, Tavares G. Evaluation of research in efciency andproductivity: A survey and analysis of the first30years of scholarly literature inDEA[J]. Socio-economic planning sciences,2008,42(3):151–157.
[43] Cooper W W, Seiford L M, Zhu J. Data envelopment analysis: History, models,and interpretations[J]. Inernational Series in Operations Research and Manage-ment Science,2011,164:1–39.
[44] Cooper W W, Seiford L M, Zhu J. Handbook on data envelopment analysis[M].Berlin: Springer,2011.
[45] Johnson A L, Kuosmanen T. One-stage and two-stage DEA estimation of theefects of contextual variables[J]. European Journal of Operational Research,2012,220(2):559–570.
[46] Lewis H F, Mallikarjun S, Sexton T R. Unoriented Two-Stage DEA: The Caseof the Oscillating Intermediate Products[J]. European Journal of OperationalResearch,2013,229(2):529–539.
[47] Friesner D, Mittelhammer R, Rosenman R. Inferring the incidence of industryinefciency from DEA estimates[J]. European Journal of Operational Research,2013,224(2):414–424.
[48] Paradi J C, Zhu H, Edelstein B. Identifying managerial groups in a large Cana-dian bank branch network with a DEA approach[J]. European Journal of Opera-tional Research,2012,219(1):178–187.
[49] Yang F, Ang S, Xia Q, et al. Ranking DMUs by using interval DEA cross ef-ficiency matrix with acceptability analysis[J]. European Journal of OperationalResearch,2012,223(2):483–488.
[50] Lee H S, Zhu J. Super-efciency infeasibility and zero data in DEA[J]. EuropeanJournal of Operational Research,2012,216(2):429–433.
[51] Fang L. A generalized DEA model for centralized resource allocation[J]. Euro-pean Journal of Operational Research,2013,228(2):405–412.
[52] R-dder W, Reucher E. Advanced X-efciencies for CCR-and BCC-models?towards Peer-based DEA controlling[J]. European Journal of Opera-tional Research,2012,219(2):467–476.
[53] Lozano S. Information sharing in DEA: A cooperative game theory approach[J].European Journal of Operational Research,2012,222(3):558–565.
[54] Krivonozhko V E, Frrsund F R, Lychev A V. A note on imposing strong com-plementary slackness conditions in DEA[J]. European Journal of OperationalResearch,2012,220(3):716–721.
[55] Sarkis J, Cordeiro J J. Ecological modernization in the electrical utility indus-try: An application of a bads-goods DEA model of ecological and technical ef-ciency[J]. European Journal of Operational Research,2012,219(2):386–395.
[56] Washio S, Yamada S, Tanaka T, et al. Improvements by analyzing the efcientfrontier in DEA[J]. European Journal of Operational Research,2012,217(1):173–184.
[57] Falagario M, Sciancalepore F, Costantino N, et al. Using a DEA-cross efciencyapproach in public procurement tenders[J]. European Journal of OperationalResearch,2012,218(2):523–529.
[58] Ouellette P, Quesnel J P, Vigeant S. Measuring returns to scale in DEA modelswhen the firm is regulated[J]. European Journal of Operational Research,2012,220(2):571–576.
[59] Vaninsky A. Prospective national and regional environmental performance:Boundary estimations using a combined data envelopment?stochastic frontieranalysis approach[J]. Energy,2010,35(9):3657–3665.
[60] Azadeh A, Asadzadeh S, Saberi M, et al. A Neuro-fuzzy-stochastic frontier anal-ysis approach for long-term natural gas consumption forecasting and behavioranalysis: The cases of Bahrain, Saudi Arabia, Syria, and UAE[J]. Applied En-ergy,2011,88(11):3850–3859.
[61] Mastromarco C, Ghosh S. Foreign Capital, Human Capital, and Efciency: AStochastic Frontier Analysis for Developing Countries[J]. World Development,2009,37(2):489–502.
[62] Manlagit M C V. Cost efciency, determinants, and risk preferences in banking:A case of stochastic frontier analysis in the Philippines[J]. Journal of AsianEconomics,2011,22(1):23–35.
[63] Holmgren J. The efciency of public transport operations? An evaluation us-ing stochastic frontier analysis[J]. Research in Transportation Economics,2013,39(1):50–57.
[64] Wang M, Wong M C S. International R&D Transfer and Technical Ef-ciency: Evidence from Panel Study Using Stochastic Frontier Analysis[J]. WorldDevelopment,2012,40(10):1982–1998.
[65] Scotti D, Malighetti P, Martini G, et al. The impact of airport competition ontechnical efciency: A stochastic frontier analysis applied to Italian airport[J].Journal of Air Transport Management,2012,22(7):9–15.
[66] Carree M A. Technological inefciency and the skewness of the error componentin stochastic frontier analysis[J]. Economics Letters,2002,77(1):101–107.
[67] Wu Y. The productive efciency of Chinese iron and steel firms A stochasticfrontier analysis[J]. Resources Policy,1995,21(3):215–222.
[68] Kraft E, Trtrolu D. Bank Efciency in Croatia: A Stochastic-Frontier Analy-sis[J]. Journal of Comparative Economics,1998,26(2):282–300.
[69] yuan Dong X, Putterman L. Productivity and Organization in China’s Rural In-dustries: A Stochastic Frontier Analysis[J]. Journal of Comparative Economics,1997,24(2):181–201.
[70] Niquidet K, Nelson H. Sawmill production in the interior of British Columbia:A stochastic ray frontier approach[J]. Journal of Forest Economics,2010,16(4):257–267.
[71] Helvoigt T L, Adams D M. A stochastic frontier analysis of technical progress,efciency change and productivity growth in the Pacific Northwest sawmill in-dustry[J]. Forest Policy and Economics,2009,11(4):280–287.
[72] Yang H H. Measuring the efciencies of Asia-pacific international airports-Parametric and non-parametric evidence[J]. Computers&Industrial Engineer-ing,2010,59(4):697–702.
[73] Cullinane K, Wang T F, Song D W, et al. The technical efciency of containerports: Comparing data envelopment analysis and stochastic frontier analysis[J].Transportation Research Part A: Policy and Practice,2006,40(4):354–374.
[74] Lim J, Nam C, Kim S, et al. Forecasting3G mobile subscription in China:A study based on stochastic frontier analysis and a Bass difusion model[J].Telecommunications Policy,2012,36(10):858–871.
[75] Fenn P, Vencappa D, Diacon S, et al. Market structure and the efciency of Euro-pean insurance companies: A stochastic frontier analysis[J]. Journal of Banking&Finance,2008,32(1):86–100.
[76]王占锋,吴耀华,赵林城.删失回归模型中一个LASSO型变量选择和估计方法(英文)[J].应用概率统计,2010(01):66–80.
[77]邵伟,祝丽萍,刘福国,等.对称阵稀疏主成分分析及其在充分降维问题中的应用[J].山东大学学报(理学版),2012(04):116–120+126.
[78]张靖,胡学钢,张玉红,等. K-split Lasso:有效的肿瘤特征基因选择方法[J].计算机科学与探索,2012(12):1136–1143.
[79]马文浩.各种Lq惩罚在变量选择中的应用及其比较[D].济南:山东大学,2012.
[80]谭理想.双线性时间序列模型的Lasso方法定阶[D].南京:南京大学,2012.
[81]梁斌,陈敏,缪柏其,等.基于LARS-Lasso的指数跟踪及其在股指期货套利策略中的应用[J].数理统计与管理,2011(06):1104–1113.
[82]王锋.基于稀疏偏最小二乘算法的生物组学数据融合算法研究[D].长春:吉林大学,2012.
[83]王娉.几种罚似然估计在广义线性模型下的性质[D].重庆:西北大学,2012.
[84]王拓.基因调控网络的线性回归模型及其鲁棒性分析[D].西安:西安电子科技大学,2012.
[85]阎春雨.广义线性模型中纠偏估计的再回归方法[D].济南:山东大学,2012.
[86]冉杨.基于Lasso极限最小学习机和LAB颜色空间的人脸识别研究[D].上海:复旦大学,2012.
[87]柯郑林. Lasso及其相关方法在多元线性回归模型中的应用[D].北京:北京交通大学,2011.
[88]孙丽丽.工具变量回归模型中的变量选择[D].长春:东北师范大学,2008.
[89]赵婷婷. AR（p）模型的Lasso方法定阶[D].长春:东北师范大学,2008.
[90]刘睿智,杜溦.基于LASSO变量选择方法的投资组合及实证分析[J].经济问题,2012(09):103–107.
[91]曲婷,王静.基于Lasso方法的平衡纵向数据模型变量选择[J].黑龙江大学自然科学学报,2012(06):715–722+726.
[92]王大荣,张忠占.线性回归模型中变量选择方法综述[J].数理统计与管理,2010(04):615–627.
[93]梁宝娟,巨永锋,张菁. MKLasso模型的算法与模型选择[J].长安大学学报(自然科学版),2012(04):105–110.
[94]施万锋,胡学钢,俞奎.一种面向高维数据的均分式Lasso特征选择方法[J].计算机工程与应用,2012(01):157–161.
[95]闫丽娜,覃婷,王彤. LASSO方法在Cox回归模型中的应用[J].中国卫生统计,2012(01):58–60+64.
[96]李平,曲博,黄光东.基于Fre′chet Copula的欧式脆弱期权定价[J].管理科学学报,2012,15(4):23–30.
[97]周孝华,张保帅,董耀武.基于Copula-SV-GPD模型的投资组合风险度量[J].管理科学学报,2012,15(12):70–78.
[98]刘喆,陶凤和,贾长治.基于Copula函数的部件相关串联机械系统可靠性分析[J].中国测试,2013,1:031.
[99]赵继超,袁越,傅质馨,等.基于Copula理论的风光互补发电系统可靠性评估[J].电力自动化设备,2013,1:027.
[100]向中华,易文德,曾胜.基于Copula函数我国林业经济发展与气候之间的关系研究[J].林业经济,2012(2):24–27.
[101]李怀宇.基于Copula和SFA的海岸带生态经济非线性研究[D].天津:天津大学,2010.
[102]王宗润,汪武超,王小丁,等.基于条件概率积分变换的多元Copula函数选择[J].管理工程学报,2012,26(3):102–108.
[103]程晓娟.资源、环境两维视角下区域生态效率DEA评价[J].当代经济管理,2013(02):63–68.
[104]未小刚.基于DEA-Malmquist指数的我国体育用品上市公司经营效率研究[J].西安体育学院学报,2013(02).
[105]肖林兴.中国全要素生产率的估计与分解―――ＤＥＡ－Ｍａｌｍｑｕｉｓｔ方法适用性研究及应用[J].贵州财经学院学报,2013(01).
[106]周方涛.基于AHP-DEA方法的区域科技创业人才生态系统评价研究[J].管理工程学报,2013(01):8–14.
[107]刘新慧,陈锦燕,周欢.流动注射法与分光光度法对环境水体中挥发酚测定的比较研究[J].现代仪器,2012(02):59–61.
[108]罗俊浩,崔娥英,季建华.基于随机前沿分析(SFA)的港口上市公司的效率评价[J].武汉理工大学学报(交通科学与工程版),2012(04):736–739.
[109]马跃如,白勇,程伟波.基于SFA的我国文化产业效率及影响因素分析[J].统计与决策,2012(08):97–101.
[110]王博文,韩先锋,卫伟.基于SFA和DEA的中国低碳企业生产效率的比较[J].统计与决策,2012(02):140–142.
[111]徐辉,李健,钟惠波.银行效率与不良贷款冲击效应的实证研究――基于SFA测度分析的应用[J].金融评论,2012(03):29–40+123–124.
[112]周末,王良举,陈甬军.中国钢铁企业的规模过小了吗?――基于NEIO和SFA方法的比较分析[J].产业经济评论,2012(01):1–17.
[113]朱承亮,师萍,安立仁.人力资本及其结构与研发创新效率――基于SFA模型的检验[J].管理工程学报,2012(04):58–64.
[114]陈春,肖光恩,陈林, et al.基于DEA的中国技术效率地区差异估算[J].武汉科技大学学报(社会科学版),2013(01):87–88–89–90.
[115]栾文敬,孙欢,宋媛媛,等.农村养老保险覆盖面投入产出效率评估与影响因素分析――基于DEA与Tobit两步法[J].华中农业大学学报(社会科学版),2013(01):84–89.
[116]刘军.运用SFA方法对我国商业银行支农金融效率的研究[D].合肥:安徽大学,2012.
[117]王丽丽.基于SFA模型的我国东部沿海各省科技创新能力研究[D].青岛:青岛理工大学,2012.
[118]张慧娟.基于SFA方法的徽商银行X-效率测度及影响因素分析[D].南京:南京大学,2012.
[119]王彦霞.秦皇岛:燕山大学,2011.
[120]王顺久,杨志峰,丁晶.关中平原地下水资源承载力综合评价的投影寻踪方法[J].资源科学,2004,26(6):104–110.
[121]杨晓华,杨志峰,郦建强.水质综合评价的遗传投影寻踪插值模型[J].环境工程,2004,22(3):69–71.
[122]严光财,方新安,马朝霞.以神经网络建立武汉地区医院建筑节能综合评价体系[J].数理医药学杂志,2005,18(1):85–86.
[123]李文博,郑文哲.基于神经网络的企业技术创新能力综合评价研究[J].科技进步与对策,2005,22(1):55–57.
[124]孟文清,石华旺,李万庆.基于人工神经网络的建筑工程质量模糊综合评[J].工程建设与设计,2004(12):67–69.
[125]刘锡健,周娟,张恒.关于石油工程项目社会效益的定量化综合评价[J].科技进步与对策,2004,21(12):141–142.
[126]肖健华.基于核方法的智能综合评价框架系统建造方法[J].宝鸡文理学院学报：自然科学版,2003,23(1):8–11,25.
[127]肖健华,吴今培.基于SVM的综合评价方法研究[J].计算机工程,2002,28(8):28–30.
[128]李栋,王洪礼,李胜朋.综合评价法的统一化研究[J].天津大学学报(社会科学版),2006,8(5):373–375.
[129]邱东.多指标综合评价方法的系统分析[M].北京:中国统计出版社,1992.
[130] Friedman J H, Stuetzle W. Projection pursuit regression[J]. J. Amer. Statist.Assoc.,1981,76:817–823.
[131] Fredman J. Multivariate adaptive regression splines(with discussion)[J]. Theannals of statistics,1991,19:1–141.
[132] Vapnik V. The Nature of Statistical Learning Theory[M]. New York: Springer,1995.
[133] Nelsen R. An Introduction to Copulas[M]. Berlin: Springer,1998.
[134]史道济,姚庆祝.改进Copula对数据拟合的方法[J].系统工程理论与实践,2004,24(4):49–55.
[135] Wang W, Wells M T. Model selection and semiparametric inference for bivari-ate failure-time data[J]. Journal of The American Statistical Association,2000,95:62–72.
[136] Fermanian J. Goodness of fit tests for copulas[J]. Journal of Multivariate Anal-ysis,2005,95:119–152.
[137] Cornelia S, Mark T. Goodness-of-fit Tests for Parametric Families ofArchimedean Copulas[R]. Münster: University of Muenster,2004.
[138] Bickel P, Rosenblatt M. On some global meansures of the deviation of densityfunction estimates[J]. Annals of Statistics,1973,1:1071–1095.
[139] Kojadinovic I, Yan J. Modeling Multivariate Distributions with ContinuousMargins Using the copula R Package[J]. Journal of Statistical Software,2010,34(9):1:20.
[140] Berg D. Copula Goodness-of-Git Testing: An Overview and Power Compari-son[J]. The European Journal of Finance,2009,15:675–701.
[141] Genest C, Remillard B, Beaudoin D. Goodness-of-fit tests for copulas: A reviewand a power study[J]. Insurance: Mathematics and Economics,2009,44:199–214.
[142] Genest C R, emillard B. Validity of the Parametric Bootstrap for Goodness-of-Fit Testing in Semiparametric Models. e Probabilit[J]. Annales de lInstitut HenriPoincar e Probabilit es et Statistiques,2008,44:1096–1127.
[143] Kojadinovic I, Yan J. A goodness-of-fit test for multivariate multiparameter cop-ulas based on multiplier central limit theorems[J]. Statistics and Computing,2011,21:17–30.10.1007/s11222-009-9142-y.
[144] Charnes C W, A., E. R. Measuring the inefciency of decision making units[J].European Journal of Operational Research,1978,2:429–444.
[145] Simar L, Wilson P. Statistical inference in nonparametric frontier models: Thestate of the art[J]. Journal of Productivity Analysis,2000,13:49–78.
[146] Cazals J F, C., Simar L. Nonparametric frontier estimation: A robust approach[J].Journal of Econometrics,2002,106:1–25.
[147] Fare R, Grosskopf S, Lindgren B, et al. Productivity changes in Swedish phar-macies1980–1989: A non-parametric Malmquist approach[J]. Journal of Pro-ductivity Analysis,1992,3:85–101.