國立臺灣大學數學系Cheng, Ming-YenMing-YenCheng2006-09-272018-06-282006-09-272018-06-282006http://ntur.lib.ntu.edu.tw//handle/246246/20060927121123929369Rice (1984) proposed a boundary modified kernel regression method which linearly combines two kernel regression estimators based on different bandwidths. In the context of density estimation, advantages of this method over two other popular approaches, local linear fitting & the boundary kernels of M¨uller (1991), are discussed. Selection of the ratio of the two bandwidths is studied. Asymptotic & exact mean squared errors are provided as tools to analyze the problem. In the case of Normal kernels, keeping the bandwidth ratio fixed, for ease & speed of implementation, & a specific bandwidth ratio are suggested.application/pdf217365 bytesapplication/pdfzh-TWboundary effectboundary kernelexact mean squared errorkernel smoothinglocal linear smoothingjournal articlehttp://ntur.lib.ntu.edu.tw/bitstream/246246/20060927121123929369/1/rice5.pdf