简介：Inthesystemofm(m≥2)seeminglyunrelatedregressions,weshowthattheGauss-Markovestimator(GME)ofanyregressioncoefficientshasuniquesimplifiedform,whichexactlyequalstotheonestepcovariance-adjustedestimatoroftheregressioncoefficients,andhenceweconcludethatforanyfinitek≥2thek-stepcovariance-adjustedestimatordegeneratestotheone-stepcovariance-adjustedestimatorandthecorrespondingtwo-stageAitkenestimatorhasexactlyonesimplifiedform.Also,theuniquesimplifiedexpressionoftheGMEisjusttheestimatorpresentedintheTheorem1ofWang’work[1988].Anewestimateofregressioncoefficientsinseeminglyunrelatedregressionsystem,ScienceinChina,SeriesA10,1033-1040].

简介：TheconcernoveroutliersisoldsinceBernoulli(see[12]),reviewedhistoricallyby[11]andupdatedwith[10]intheirencyclopediatextbook.Jamesetal.[46]usedsimulationtechniquetocomparesomerecentpublishedoutlierdetectionprocedures.Thehistoryofadeptanddiagnosisofoutliersistracedfromoldandpresencecomments.Theil-typeorRank,Brown-Mood,Lp,M,adaptiveM,GM,andTrimmed-Winsorizationestimatorsarethemostpopularestimatorsthatwewillreviewinthispaperasanapplicationtooutlieraccommodation.Wewillreviewandcomparethemostnumericalandgraphicaldisplaysbasedonresidualstoflagoutliers.

简介：RecentlyR.S.SinghhasstudiedtheempiricalBayes（EB）estimationinamultiplelinearregressionmodel.InthispaperweconsidertheEBtestofregressioncoefficientβforthismodel.WeworkouttheEBtestdecisionrulebyusingkernelestimationofmultivariatedensityfunctionanditsfirstorderpartialderivatives.Weobtainitsasymptoticallyoptimal（a.o.）propertyundertheconditionE||β||1<∞.ItisshownthattbeconvergenceratesofthisEBtestdecisionruleareO(n-（r-1）λ/p+r)undertheconditionE||β||pr/2-λ<∞.whereanintegerr>l,0

简介：APoissonregressionmodelandanegativebinomialregressionmodel(NBmodel)areoftenusedinareassuchasmedicineandeconomy,butrarelyinthedomesticforestrysector,especiallyintheforestfireforecasting.BasedonthedataofforestfireoccurrencesinDaxing’anlingregionin1980-2005,thispaperprofoundlyanalyzestheapplicationconditionsandtestmethodsofthetwomodels.TheAICmethodwasusedtocheckthefittinglevelofthemodelsandthecapabilityofthemodelsforforecastingforestfireswasdiscussed.ThisstudyprovidednecessarytheoreticalbasisanddatasupportfortheapplicationofthetwomodelsinthefieldofforestryinChina.

简介：Fittinglogarithmicbln(clx),a+bln(c+x)orreciprocalb/(c+x),a+b/(c+x)regressionmodelstodatabytheleastsquaresmethodasksforthedeterminationoftheclosureofthesetofeachtypeofthesefunctionsdefinedonafinitedomain.Itfollowsthataminimalsolutionmaynotexist.Butitdoesexistwhentheclosureisconsidered.

简介：这篇论文与ε～N为线性回归模型y=Xβ+ε的参数β考虑实验Bayes(EB)评价问题(0，σ2我)给定的β。把标准和均方差矩阵(MSEM)标准基于皮特曼亲密(PC)，我们在平常的最不方形的评估者(OLSE)上证明EB评估者的优势。

简介：Twodiagnosticsarepresentedforthetransformationofexplanatoryvariablesinregression.OneisbasedonthelikelihooddisplacementproposedbyCookandWeisberg(1982)forassessingtheinfluenceofindividualcasesonthemaximumlikelihoodestimateofatransformationparameter.Theotherisbasedonthelocalin-fluencetheoryproposedbyCook(1986)forassessingtheinfluenceofsmallperturba-tionsontheparameterestimates.Computationsarcperformedforadatasettoillus-tratetheusefulnessofthesediagnostics.

简介：Researchonjumpregressionfunc(?)onshasnotbeenadequateyetAccordingtotheinformationaboutthenumberofjumps,theirpositionsandjumpmagnitudes,jumpregressionfunctionscanbeclassifiedintoeighttypes.Thispaperdealsespeciallywiththesecondjumpregressionfunction.Firstofall,aconceptoftrimmedsplineestimateisproposedandwithitanL~2-consistentestimateofthesmoothingpartofthejumpregressionfunctionisobtained.ThisalongwiththeL~2-consistentestimateofjumpmagnitudeconstitutesanestimateofthesecondjumpregressionfunction.Thispaperdiscussesalsothecasethatthejumppositionshavesomeindeterminacy.Anewcriterionissuggestedanditsuniquesolutionderived.Intheend,afewnumericalresultsaregiven.

简介：AbstractIt has been reported that liver fibrosis could be reversed after eliminating liver injuries. This article systematically summarizes the evidence of fibrosis regression based on histology, liver stiffness, and serum biomarkers, and discusses several clinically relevant challenges. Evidence from liver biopsy has been regarded as the gold standard in the assessment of fibrosis regression. Semi-quantitative staging and grading systems are traditionally and routinely used to define regression. Recently, the predominantly regressive, indeterminate, and predominantly progressive score was proposed, based on the regressive features from "hepatic repair complex" , to provide additional information regarding the quality of fibrosis. For non-invasive assessment, although liver stiffness and serum biomarkers could be applied to reflect the dynamic changes of liver fibrosis, other confounding factors such as liver inflammation have to be considered. In conclusion, both histology and non-invasive methods can provide evidence regarding fibrosis regression. The predictive value of fibrosis regression in long-term prognosis warrants further investigation.

简介：在这份报纸，我们建议本地人的一个新方法为nonparametric的线性适应变光滑有条件的quantile回归。过程的一些理论性质被调查。然后，我们在一个模仿的例子上表明方法的表演并且把它与另外的方法作比较。模拟结果证明当内在的图象是线性的piecewise或能被如此的图象接近时，我们的方法的合理表演特别处于状况求婚了。一般来说，我们的方法在吝啬的方形的评价(MSE)和吝啬的绝对评价(MAE)的意义超过大多数另外的存在方法标准。过程关于增加噪音水平是很稳定的，算法能容易被用于更高维的状况。

简介：

简介：

简介：ＯＮＢＡＨＡＤＵＲＡＳＹＭＰＴＯＴＩＣＥＦＦＩＣＩＥＮＣＹＩＮＡＳＥＭＩＰＡＲＡＭＥＴＲＩＣＲＥＧＲＥＳＳＩＯＮＭＯＤＥＬ￥ＬＩＡＮＧＨｕａ；ＣＨＥＮＧＰｉｎｇ（ＩｎｓｔｉｔｕｔｅｏｆＳｙｓｔｅｍｓＳｃｉｅｎｃｅ，ＡｃｏｄｅｍｉａＳｉｎｉｃａ，Ｂｅｉ...

简介：

简介：Twostatisticalmodelsoftheconcentrationofsuspendedsedimentonmudcoastshavebeendevelopedbyusingthestepwiseregressionmethod.ThestatisticalanalysisinthispaperisbasedonthefielddataofthemudcoastofLianyungang,China.Theregressionmodelsprovideanessentiallycompletestatisticaldescriptionoftheprocessesoffine-grainedsedimentonopenmudcoasts.

简介：TheauthorsgiveMLEθ1MLofθ1inthemodelY=θ1+g(T)-σ,thenconsiderBahadurasymptoticefficiencyofθ1ML,whereTandεareindependent,gisunknown,ε～φ(-)isknownwithmean0andvarianceσ^2.

简介：Withtheexpansionofthegeneexpressionprofiledatabase,inthecaseofaslittleaspossibletoloseinformationortoretainthemostcriticalinformation,geneextractionhasbecomeamaindirectionforthescholars.Thispaperexcludes1561irrelevantgenesthroughthedefinitionofweighteddistancefirstly,andthenremoves252redundantgenesbyPearson'scorrelationcoefficient.Finallybycomparingthetwomethods,stepwiseregressionafterclusteringandonlystepwiseanalysis,weobtainthebestcombinationof8genes.

简介：这份报纸采用惩罚大量的最少的广场方法同时选择变量并且估计为高度维的covariate的系数调整了线性回归模型。弄歪的变量被假定与被看得见的covariate的一个未知函数的值决定的一个趋于增加的因素被污染。作者证明在一些适当条件下面，惩罚大量的最少的广场评估者有所谓的神谕性质。另外，作者也建议一个BIC标准选择调节参数，并且证明那个BIC标准能一致地识别真正的模型因为covariate调整了线性回归模型。模拟研究和一个真实数据被用来说明建议评价算法的效率。

简介：Oftenthelifecycledataoccurascountofthevitaleventsandarerecordedasintegers.Thepurposeofthisarticleistomodelthefertilitybehaviorbasedonreligious,educational,economic,andoccupationalcharacteristics.TheresponsesofclassifiedgroupsaccordingtothesedeterminantsareexaminedforsignificantinfluenceonfertilityusingPoissonregressionmodel(PRM)basedontheNationalFamilyHealthSurvey-3dataset.TheobservedandpredictedprobabilitiesunderPRMindicatemodalvalueoftwochildrenforthePoissondistributionmodeleddata.Presenceofdominanceoftwochildinthedatamotivatestheauthorstoadoptmultinomialregressionmodel(MRM)inordertolinkfertilitywithvarioussocioeconomicindicatorsresponsibleforfertilityvariation.Choiceoftheexplanatoryfactorsislimitedtotheavailabilityofdata.Trendsandpatternsofpreferenceforbirthcountssuggestthatreligion,caste,wealth,femaleeducation,andoccupationarethedominantfactorsshapingtheobservedbirthprocess.Empiricalanalysissuggeststhatboththemodelsusedinthestudyperformsimilarlyonthesampledata.However,fittingofMRMbytakingbirthcountoftwoascomparisoncategoryshowsimprovedAkaikeinformationcriterionandconsistentAkaikeinformationcriterionvalues.CurrentworkcontributestotheexistingliteratureasitattemptstoprovidemoreinsightintothedeterminantsofIndianfertilityusingPoissonandMRM.

简介：ＲＡＮＤＯＭＷＥＩＧＨＴＩＮＧＡＰＰＲＯＸＩＭＡＴＩＯＮＩＮＬＩＮＥＡＲＲＥＧＲＥＳＳＩＯＮＭＯＤＥＬＳＳＨＩＪＩＡＮ（ＤｅｐａｒｔｍｅｎｔｏｆＰｒｏｂａｂｉｌｉｔｙａｎｄＳｔａｔｉｓｔｉｃｓ，ＰｅｋｉｎｇＵｎｉｖｅｒｓｉｔｙ，Ｂｅｉｊｉｎｇ１００８...