Nonparametric Density Estimation
Smoothing is one of the most fundamental techniques in nonparametric function estimation. It usually refers to one-dimensional scatterplot smoothing and density estimation. It serves as a useful building block for nonparametric estimation in a multidimensional setting. Smoothing arose first from spectral density estimation in time series. In a discussion of the seminal paper by Bartlett (1946), Henry E. Daniels suggested that a possible improvement on spectral density estimation could be made by smoothed periodograms. The theory and techniques were then systematically developed by Bartlett (1948, 1950). Thus, smoothing techniques were already prominently featured in time series analysis over half a century ago.
KeywordsMean Square Error Kernel Function Density Estimation Kernel Density Kernel Density Estimation
Unable to display preview. Download preview PDF.