bw_tt_pi {kdecopula} | R Documentation |
Nearest-neighbor bandwidth selection for the tapered transformation estimator
Description
The smoothing parameters are selected by the method of Wen and Wu (2015).
Usage
bw_tt_pi(udata, rho.add = TRUE)
bw_tt_cv(udata, rho.add = T)
Arguments
udata |
data. |
rho.add |
logical; whether a rotation (correlation) parameter shall be included. |
Value
Optimal smoothing parameters as in Wen and Wu (2015): a numeric
vector of length 4; entries are (h, \rho, \theta_1, \theta_2)
.
Author(s)
Kuangyu Wen
References
Wen, K. and Wu, X. (2018). Transformation-Kernel Estimation of Copula Densities Journal of Business & Economic Statistics, 38(1), 148–164.
[Package kdecopula version 0.9.3 Index]