Exact Mean Integrated Squared Error
James Stephen Marron, MATTHEW P. WAND · The Annals of Statistics · 1992
An exact and easily computable expression for the mean integrated squared error (MISE) for the kernel estimator of a general normal mixture density, is given for Gaussian kernels of arbitrary order. This provides a powerful new way of understanding density estimation which complements the usual tools of simulation and asymptotic analysis. The family of normal mixture densities is very flexible and the formulae derived allow simple exact analysis for a wide variety of density shapes. A number of applications of this method giving important new insights into kernel density estimation are presented. Among these is the discovery that the usual asymptotic approximations to the MISE can be quite inaccurate, especially when the underlying density contains substantial fine structure and also strong evidence that the practical importance of higher order kernels is surprisingly small for moderate sample sizes.
Cited by 750 works. doi:10.1214/aos/1176348653 Open-access PDF
Authors
References
- Density Estimation for Statistics and Data Analysis
- Kernels for Nonparametric Curve Estimation
- Oversmoothed Nonparametric Density Estimates
- Some Errors Associated with the Non-parametric Estimation of Density Functions
- Estimation non paramétrique de la densité par histogrammes généralisés
- Gaussian‐based kernels
- Estimation of the Scaling Parameter for a Kernel Type Density Estimate
- Efficiency of a Kernel Density Estimator Under an Autoregressive Dependence Model
- A note on jackknifing kernel regression function estimators (Corresp.)