简介:Researchonjumpregressionfunc(?)onshasnotbeenadequateyetAccordingtotheinformationaboutthenumberofjumps,theirpositionsandjumpmagnitudes,jumpregressionfunctionscanbeclassifiedintoeighttypes.Thispaperdealsespeciallywiththesecondjumpregressionfunction.Firstofall,aconceptoftrimmedsplineestimateisproposedandwithitanL~2-consistentestimateofthesmoothingpartofthejumpregressionfunctionisobtained.ThisalongwiththeL~2-consistentestimateofjumpmagnitudeconstitutesanestimateofthesecondjumpregressionfunction.Thispaperdiscussesalsothecasethatthejumppositionshavesomeindeterminacy.Anewcriterionissuggestedanditsuniquesolutionderived.Intheend,afewnumericalresultsaregiven.
简介:Thebilevelprogrammingisappliedtosolvehierarchicalintelligencecontrolproblemsinsuchfieldsasindustry,agriculture,transportation,military,andsoon.Thispaperpresentsaquadraticobjectivepenaltyfunctionwithtwopenaltyparametersforinequalityconstrainedbilevelprogramming.Undersomeconditions,theoptimalsolutiontothebilevelprogrammingdefinedbythequadraticobjectivepenaltyfunctionisprovedtobeanoptimalsolutiontotheoriginalbilevelprogramming.Moreover,basedonthequadraticobjectivepenaltyfunction,analgorithmisdevelopedtofindanoptimalsolutiontotheoriginalbilevelprogramming,anditsconvergenceprovedundersomeconditions.Furthermore,undertheassumptionofconvexityatlowerlevelproblems,aquadraticobjectivepenaltyfunctionwithoutlowerlevelproblemsisdefinedandisprovedequaltotheoriginalbilevelprogramming.
简介:Intheanalysisoneconomicgrowthfactors,calculatingthecontributionrateofinfluencingfactortoeconomicgrowthusingtheCESproductionfunctionmodelisacommonandimportantresearchfield.TheCESproductionfunctionmodelhasavarietyofforms,andthesuperpositionCESproductionfunctionmodelproposedinthepaperisanewmodel.Withregardtothemodel’sparameterestimation,thepaperproposesamodifiedparticleswarmoptimizationwhichhasafastconvergencerateandahighprecision.Withregardtothecalculationoffactorcontributionrate,thepaperoffersanewscientificcalculationmethodwiththesuperpositionCESproductionfunctionmodel.Atlast,thepapermakesanempiricalanalysisonthecontributionrateofChineseeconomicgrowthfactorsandtheresultobtainedconsistswiththereality.
简介:ThepurposeofthispaperistoinvestigatethepricingEuropeancalloptionvaluationproblemsundertheexerciseprice,maturity,risk-freeinterestrate,andthevolatilityfunction.Anadvancemethodology,Chebyshevsimulatedannealingneuralnetwork(ChSANN),isenforcedfortheBlack-Scholes(B-S)modelwithboundaryconditions.OurschemeisstableandeasytoimplementonB-Sequation,forarbitraryvolatilityandarbitraryinterestratevalues.Also,thecomparativeresultsdemonstratethattheattainedapproximatesolutionsareconvergingtowardstheexactsolution.ThegraphicalresultsshowthattheincreasingflowoftheEuropeancalloptionastheexponentialincreasetakesplaceinassets.Thepresentedalgorithmcanbefurtherappliedtootherfinancialmodelswithcertainboundaryconditions.Thealgorithmofthemethodshowsthattheapproachcanalsobeeasilyemployedontime-fractionalB-Sequation.
简介:Inthispaper,thedefinitionsofBayesestimator,minimaxestimator,minimumriskequivariantestimatorandadmissibleestimatorunderthegeneralmatrixlossfunctionaregiven.Severalresultsonestimationofparameterswiththeordinarylossfunctionareextendedtothecaseofthematrixlossfunction.
简介:Inarecentarticle,theauthorsprovidedaneffectivealgorithmforbothcomputingtheglobalinfimumof/anddecidingwhetherornottheinfimumof/isattained,where/isamultivariatepolynomialoverthefieldRofrealnumbers.Asacomplement,theauthorsinvestigatethesemialgebraicallyconnectedcomponentsofminimumpointsofapolynomialfunctioninthispaper.Foragivenmultivariatepolynomial/overR,itisshownthattheabove-mentionedalgorithmcanfindatleastonepointineachsemi-algebraicallyconnectedcomponentofminimumpointsof/whenever/hasitsglobalminimum.
简介:Stronguniformconsistencyratesaregivenforkerneltypeestimatorsoftheconditionalfunctionwith(?)-mixingsample.Especially,fornonparametricestimatorsofkerneldensity,theregressionfunctionwhenYisbounded,conditionaldf’s,L-smoothingandM-smoothing,weobtainthesamerateO((n/logn)-1/3)asinthei.i.d.sampleestablishedbyH(?)rdle,JanssenandSerfling.
简介:EXTREMEPOINTRESULTSFORSTRICTPOSITIVEREALNESSOFTRANSFERFUNCTIONFAMILIESWANGLong;HUANGLin(DopartmentofMechanics,PekingUniversit...
简介:Thispaperconsiderstheconvergenceratesfornonparametricestimatorsoftheerrordistributioninsemi-parametricregressionmodels.Byestablishingsomegenerallawsoftheiteratedlogarithm,itshowsthattheratesofconvergenceofeithertheempiricaldistributionorasmoothedversionoftheempiricaldistributionfunctionmatchesexactlytheratesobtainedforanindependentsamplefromtheerrordistribution.
简介:
简介:这份报纸与错过反应数据的nonignorable考虑分发函数和quantiles的评价问题。三条途径被开发估计分发功能和quantiles,即,Horvtiz-Thompson-type方法,回归归罪方法和扩充反的概率加权的途径。倾向分数被semiparametric指定指数的倾斜模型。为了在倾向估计倾斜的参数,得分,作者建议一个调整实验可能性的方法处理过去识别的系统。在一些常规条件下面,作者调查asymptotic性质为分发功能和quantiles建议了三个评估者,并且发现这些评估者有一样的asymptotic变化。大折刀方法被采用一致地估计asymptotic变化。模拟研究被进行调查建议方法论的有限样品表演。
简介:这份报纸讨论吝啬地的向后的随机的微分方程(吝啬地的BSDE)与跳并且控制吝啬地的BSDE与的一种新类型跳,也就是吝啬地的BSDE与强烈跳结合了联系控制问题的价值功能。作者首先为BSDE的上述二种类型证明存在和唯一以及一条比较定理。为这,作者使用一个近似方法。在Peng在1997介绍的随机的向后的semigroups的观点的帮助下,然后,作者为值函数得到动态编程原则(DPP)。而且,作者证明值函数是integro部分的微分方程,它在连续函数的一个足够的空格唯一由Barles介绍了的联系非局部的Hamilton-Jacobi-Bellman(HJB)的一个粘性解决方案,等。在1997。
简介:Intheanalysisoneconomicgrowthfactors,researchersusuallyusetheproductionfunctionmodeltocalculateandmeasureinfluencingfactors’contributionratestoeconomicgrowth.CommonproductionfunctionsincludetheCD(Cobb-Douglas)productionfunction,theCES(ConstantElasticityofSubstitution)productionfunction,theVES(VariableElasticityofSubstitution)productionfunction,andsoon.Inconsiderationofthediversityandcomplementarityofmodels,thepapercombinestheCDproductionfunctionwiththeCESproductionfunctionandthenproposesamixedproductionfunction.Withregardtotheparameterestimationofmodel,thepapergivesanimprovedfireflyalgorithmwiththehighprecisionandafastrateofconvergence.Withregardtothecalculationoffactors’contributionrates,traditionalmethodsgenerallyhavebigerrorsandarenotapplicabletocomplicatedmodels,sothepaperoffersanewmethodwhichcancalculatecontributionratesscientifically.Finally,thepapercalculatesthecontributionratesoffactorsaffectingChineseeconomicgrowthandgetsagoodresult.