A Review and Comparison of Bandwidth Selection Methods for Kernel Regression

Over the last four decades, several methods for selecting the smoothing parameter, generally called the bandwidth, have been introduced in kernel regression. They differ quite a bit, and although there already exist more selection methods than for any other regression smoother we can still see coming up new ones. Given the need of automatic data-driven bandwidth selectors for applied statistics, this review is intended to explain and compare these methods.