fpower: Folded Power Transformation

In jhmaindonald/qra: Quantal Response Analysis for Dose-Mortality Data

Folded Power Transformation

Description

The name “folded Power Transformation” is used because this does for power transformations what Tukey's folded logarithm does for the logarithmic tranformation. The function calculates

f(p, \lambda, \epsilon) = \frac{p+\epsilon}{1-p+\epsilon}^\lambda

where \lambda is the power and \epsilon is a positive offset that ensures that \frac{p+\epsilon}{1-p+\epsilon} is greater than 0 and finite.

Usage

fpower(p, lambda, eps)

Arguments

p	Mortality proportion
lambda	Power lambda for the power transformation
eps	If eps>0 phat is replaced by \frac{p+\epsilon}{1+\epsilon} before applying the power transformation.

Value

The transformed values of fpower(p).

Examples

p <- (0:10)/10
ytrans <- fpower(p, lambda=0.25, eps=1/450)

jhmaindonald/qra documentation built on Nov. 14, 2023, 3:16 p.m.