Presentation - Introduction to Kernel Smoothing

Presentation - Introduction to Kernel Smoothing

ID:40696587

大小:141.66 KB

页数:24页

时间:2019-08-06

Presentation - Introduction to Kernel Smoothing_第1页
Presentation - Introduction to Kernel Smoothing_第2页
Presentation - Introduction to Kernel Smoothing_第3页
Presentation - Introduction to Kernel Smoothing_第4页
Presentation - Introduction to Kernel Smoothing_第5页
资源描述:

《Presentation - Introduction to Kernel Smoothing》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、IntroductiontoKernelSmoothing0.0060.004Density0.0020.0007008009001000110012001300WilcoxonscoreM.P.Wand&M.C.JonesKernelSmoothingMonographsonStatisticsandAppliedProbabilityChapman&Hall,1995.StefanieScheid-IntroductiontoKernelSmoothing-January5,20041IntroductionHistogramofsomep−values121086D

2、ensity4200.00.20.40.60.81.0p−valuesStefanieScheid-IntroductiontoKernelSmoothing-January5,20042Introduction{Estimationoffunctionssuchasregressionfunctionsorprobabilitydensityfunctions.{Kernel-basedmethodsaremostpopularnon-parametricestimators.{Canuncoverstructuralfeaturesinthedatawhichapar

3、ametricapproachmightnotreveal.StefanieScheid-IntroductiontoKernelSmoothing-January5,20043UnivariatekerneldensityestimatorGivenarandomsampleX1;:::;Xnwithacontinuous,univariatedensityf.Thekerneldensityestimatorisnf^(x;h)=1XxXiKnhhi=1withkernelKandbandwidthh.Undermildconditions(hmustdecre

4、asewithincreasingn)thekernelestimateconvergesinprobabilitytothetruedensity.StefanieScheid-IntroductiontoKernelSmoothing-January5,20044ThekernelK{Canbeaproperpdf.Usuallychosentobeunimodalandsymmetricaboutzero.)Centerofkernelisplacedrightovereachdatapoint.)In uenceofeachdatapointisspreadabo

5、utitsneighborhood.)Contributionfromeachpointissummedtooverallestimate.StefanieScheid-IntroductiontoKernelSmoothing-January5,20045Gaussiankerneldensityestimate1.51.00.5●●●●●●●●●●0.0051015StefanieScheid-IntroductiontoKernelSmoothing-January5,20046Thebandwidthh{Scalingfactor.{Controlshowwide

6、theprobabilitymassisspreadaroundapoint.{Controlsthesmoothnessorroughnessofadensityestimate.)Bandwidthselectionbearsdangerofunder-oroversmoothing.StefanieScheid-IntroductiontoKernelSmoothing-January5,20047Fromover-toundersmoothingKDEwithb=0.1121086Density4200.00.20.40.60.81.0p−valuesStefan

7、ieScheid-IntroductiontoKernelSmoothing-January5,20048Fromover-toundersmoothingKDEwithb=0.05121086Density4200.00.20.40.60.81.0p−valuesStefanieScheid-IntroductiontoKernelSmoothing-January5,20049Fromover-toundersmoothingKDEwithb=0.02121086Density4200.00.20.40.60.81.0p−

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。