sn.i, tn.i {NPHazardRate} | R Documentation |
Implements the local kernel weights which are used in the implementation of LocLinEst
and the second derivative estimate used in PlugInBand
.
sn.0(xin, xout, h, kfun)
sn.1(xin, xout, h, kfun)
sn.2(xin, xout, h, kfun)
sn.3(xin, xout, h, kfun)
sn.4(xin, xout, h, kfun)
sn.5(xin, xout, h, kfun)
sn.6(xin, xout, h, kfun)
tn.0(xin, xout, h, kfun, Y)
tn.1(xin, xout, h, kfun, Y)
tn.2(xin, xout, h, kfun, Y)
tn.3(xin, xout, h, kfun, Y)
xin |
A vector of data points, typicaly these are the bin centers. Missing values not allowed. |
xout |
A vector of data points where the estimate will be evaluated. |
h |
A scalar. The bandwidth to use. |
kfun |
The kernel function to use. |
Y |
Empirical hazard rate estimates. |
The functions calculate the quantities
S_{n,l}(x) = \sum_{i=1}^n K \left (\frac{x_i-x}{h}\right ) (x_i-x)^l, l=0,\dots,6
and
T_{n,l}(x) = \sum_{i=1}^n K \left (\frac{x_i-x}{h}\right ) (x_i-x)^l Y_i, l=0,\dots,3
These qunatities are used to adjust the hazard rate estimate and its second derivative in the boundary.
The weight of the functional at x