nlr (version 0.1-3)

sqrtvat: Compute square root of vairiance attribute.

Description

Transform variance to standard deviation with all its gradient and hessian.

Usage

sqrtvat(varcomp)

Arguments

varcomp

Is (n*1) vector of some variance, transform to \(\sqrt (vc)\), with attributes attr(vc,"gradient"), \(n \times p\) gradient. And attr(vc,"hessian"), \(n \times p \ times{p}\) hessian.

Value

Standard deviation is equal the square root of variance, with Gradient equal to: $$Gradient (sdev) = \frac{1}{2} \sqrt{Var} \times Gradient (Var)$$ and hessian is equal $$ hessian(sdev) = \frac{1}{2} \sqrt{vc} \times hesian(vc) - (\frac{1}{4} \sigma ^ 3) grad(vc)^T \%m3d\% grad(vc) $$

Details

For computation purpose to transform variance function values to standard deviation function value is used.

References

Riazoshams H, Midi H, and Ghilagaber G, 2018,. Robust Nonlinear Regression, with Application using R, Joh Wiley and Sons.

See Also

nlr

Examples

# NOT RUN {
## The function is currently defined as
"sqrtvat"
# }