mle.gpd: Parameter estimation for GPD

In minh2182000/gpd:

Description

mle.gpd estimates parameters for Generalized Pareto Distribution with right-censored data using Maximum Likelihood

Usage

mle.gpd(time, censor = rep(1, times = length(time)))

Arguments

time	Time to failure or termination
censor	Observation/censor indicator (1=observed, 0=right-censored), default to be all observations

Details

Generalized Pareto distribution: CDF F(x,k,a) = 1 - (1-kx/a)^(1/k) if k!=0 or 1 - e^(-x/a) if k=0

Algorithm was described in: Pham, M. H., Tsokos, C. P., Choi, B. (2018). Maximum Likelihood Estimation for the Generalized Pareto Distribution and Goodness-Of-Fit Test with Censored Data. Journal of Modern Applied Statistical Methods, 17(2).

Value

returns a vector of size 2. The first element is the estimate of k, the second is the estimate of alpha

Examples

data(melanoma, package = "boot")
status = ifelse(melanoma$status == 1, 1, 0)
mle.gpd(melanoma$time, status)

minh2182000/gpd documentation built on May 29, 2019, 5:44 a.m.