Hlscv(x, Hstart, kfold=1)
Hlscv.diag(x, Hstart, binned=FALSE, bgridsize, kfold=1)
hlscv(x, binned=TRUE, bgridsize)
binned=TRUE
hlscv
is the univariate SCV
selector of Bowman (1984) and Rudemo (1982). Hlscv
is a
multivariate generalisation of this. Use Hlscv
for full bandwidth matrices and Hlscv.diag
for diagonal bandwidth matrices.
For d = 1, 2, 3, 4 and binned=TRUE
,
estimates are computed over a binning grid defined
by bgridsize
. Otherwise it's computed exactly.
If Hstart
is not given then it defaults to
k*var(x)
where k = $\left[\frac{4}{n(d+2)}\right]^{2/(d+4)}$, n = sample size, d = dimension of data.
For large samples, k-fold bandwidth selection can significantly reduce computation time. The full data sample is partitioned into k sub-samples and a bandwidth matrix is computed for each of these sub-samples. The bandwidths are averaged and re-weighted to serve as a proxy for the full sample selector.
Rudemo, M. (1982) Empirical choice of histograms and kernel density estimators. Scandinavian Journal of Statistics. 9, 65-78. Sain, S.R, Baggerly, K.A & Scott, D.W. (1994) Cross-validation of multivariate densities. Journal of the American Statistical Association. 82, 1131-1146.
Hbcv
, Hscv
library(MASS)
data(forbes)
Hlscv(forbes)
Hlscv.diag(forbes, binned=TRUE)
hlscv(forbes$bp)
Run the code above in your browser using DataLab