R Graphical Manual

Browse All

Last data update: 2014.03.03

R: Bandwidth choice for Interval-Censored Kernel Density...

bickde

R Documentation

Bandwidth choice for Interval-Censored Kernel Density Estimation

Description

Likelihood Cross-Validation bandwidth choice for interval-censored kernel density estimates. Also computed is the direct-plug-in estimate (using the KernSmooth function dpik based on the interval midpoints.

Usage

bickde(data, factor)

Arguments

`data`	A matrix with two columns, consisting of left and right endpoints of the interval data
`factor`	A scalar factor which gives upper and lower bounds for the initial interval for the golden section search relative to a preliminary value computed by dpik.

Default value is 10 which specifies an initial interval of (dpik/10, dpik*10).

Details

Maximization of the likelihood is accomplished by golden section search using the optimize() function. This can be very SLOW.

Value

A scalar value.

Author(s)

W.J. Braun

References

Braun, J., Duchesne, T. and Stafford, J.E. (2005) Local likelihood density estimation for interval censored data. Canadian Journal of Statistics 33: 39-60.

Examples

# Not run
# bickde(ICHemophiliac)