Unbiased Cross-Validation for Bandwidth Selection

Uses unbiased cross-validation to select the bandwidth of a Gaussian kernel density estimator.

ucv(x, nb = 1000, lower, upper)

Arguments

x

a numeric vector
nb

number of bins to use.
lower, upper

Range over which to minimize. The default is almost always satisfactory.

Value

a bandwidth.

References

Scott, D. W. (1992) Multivariate Density Estimation: Theory, Practice, and Visualization. Wiley.

Venables, W. N. and Ripley, B. D. (2002) Modern Applied Statistics with S. Fourth edition. Springer.

See also

bcv, width.SJ, density

Examples

ucv(geyser$duration)
#> Warning: minimum occurred at one end of the range
#> [1] 0.1746726