資源描述:
《Partially Linear Models》由會(huì)員上傳分享,免費(fèi)在線閱讀,更多相關(guān)內(nèi)容在學(xué)術(shù)論文-天天文庫(kù)。
1、PARTIALLYLINEARMODELSWolfgangH?ardleInstitutf?urStatistikundOkonometrie?Humboldt-Universit?atzuBerlinD-10178Berlin,GermanyHuaLiangDepartmentofStatisticsTexasA&MUniversityCollegeStationTX77843-3143,USAandInstitutf?urStatistikundOkonometrie?Humboldt-Universit?atzuBerlinD-10178Berlin,GermanyJiti
2、GaoSchoolofMathematicalSciencesQueenslandUniversityofTechnologyBrisbaneQLD4001,AustraliaandDepartmentofMathematicsandStatisticsTheUniversityofWesternAustraliaPerthWA6907,AustraliaiiInthelasttenyears,therehasbeenincreasinginterestandactivityinthegeneralareaofpartiallylinearregressionsmoothingi
3、nstatistics.Manymethodsandtechniqueshavebeenproposedandstudied.Thismonographhopestobringanup-to-datepresentationofthestateoftheartofpartiallylinearregressiontechniques.Theemphasisofthismonographisonmethodologiesratherthanonthetheory,withaparticularfocusonapplicationsofpartiallylinearregressio
4、ntechniquestovariousstatisticalproblems.Theseproblemsincludeleastsquaresregression,asymptoticallyecientestimation,bootstrapresampling,censoreddataanalysis,linearmeasurementerrormodels,nonlinearmeasurementmodels,nonlinearandnonparametrictimeseriesmodels.Wehopethatthismonographwillserveasausef
5、ulreferencefortheoreticalandappliedstatisticiansandtograduatestudentsandotherswhoareinterestedintheareaofpartiallylinearregression.Whileadvancedmathematicalideashavebeenvaluableinsomeofthetheoreticaldevelopment,themethodologicalpowerofpartiallylinearregressioncanbedemonstratedanddiscussedwith
6、outadvancedmathematics.Thismonographcanbedividedintothreeparts:partone{Chapter1throughChapter4;parttwo{Chapter5;andpartthree{Chapter6.Intherstpart,wediscussvariousestimatorsforpartiallylinearregressionmodels,establishtheo-reticalresultsfortheestimators,proposeestimationprocedures,andimplemen
7、ttheproposedestimationproceduresthroughrealandsimulatedexamples.Thesecondpartisofmoretheoreticalinterest.Inthispart,weconstructseveraladaptiveandecientestimatesfortheparametriccomponent.WeshowthattheLSestimatoroftheparametriccomponentcanbemo