BCV bandwidth matrix for bivariate data.

```
Hbcv(x, whichbcv=1, Hstart, binned=FALSE, amise=FALSE, verbose=FALSE)
Hbcv.diag(x, whichbcv=1, Hstart, binned=FALSE, amise=FALSE, verbose=FALSE)
```

x

matrix of data values

whichbcv

1 = BCV1, 2 = BCV2. See details below.

Hstart

initial bandwidth matrix, used in numerical optimisation

binned

flag for binned kernel estimation. Default is FALSE.

amise

flag to return the minimal BCV value. Default is FALSE.

verbose

flag to print out progress information. Default is FALSE.

BCV bandwidth matrix. If `amise=TRUE`

then the minimal BCV value is returned too.

Use `Hbcv`

for unconstrained bandwidth matrices and `Hbcv.diag`

for diagonal bandwidth matrices. These selectors are only
available for bivariate data. Two types of BCV criteria are
considered here. They are known as BCV1 and BCV2, from Sain, Baggerly
& Scott (1994) and only differ slightly. These BCV
surfaces can have multiple minima and so it can be quite difficult to
locate the most appropriate minimum. Some times, there can be no local minimum at all so there
may be no finite BCV selector.

For details about the advanced options for `binned`

, `Hstart`

, see `Hpi`

.

Sain, S.R, Baggerly, K.A. & Scott, D.W. (1994)
Cross-validation of multivariate densities. *Journal of the
American Statistical Association*. **82**, 1131-1146.

```
# NOT RUN {
data(unicef)
Hbcv(unicef)
Hbcv.diag(unicef)
# }
```

Run the code above in your browser using DataLab