Local Inferential Feature Significance for Multivariate Kernel Density Estimation

Local inferential feature significance for multivariate kernel density estimation.

Introduction

The feature package contains functions to display and compute kernel density estimates, significant gradient and significant curvature regions. Significant gradient and/or curvature regions often correspond to significant features (e.g. local modes).

There are two main functions in this package. featureSignifGUI() is the interactive function where the user can select bandwidths from a pre-defined range. This mode is useful for initial exploratory data analysis. featureSignif() is the non-interactive function. This is useful when the user has a more definite idea of suitable values for the bandwidths. The latter is closely related to the ks::kfs() function.

For a more detailed example for 1-, 2- and 3-d data, see vignette("feature").

Installation

Install from CRAN:

install.packages("feature")

Further reading

Duong, T., Cowling, A., Koch, I., and Wand, M. P. (2008) Feature significance for multivariate kernel density estimation Computational Statistics and Data Analysis 52, 4225--4242.