AHMLE: Overall Survival AH model.

In AHSurv: Flexible Parametric Accelerated Hazards Models

Overall Survival AH model.

Description

The flexible parametric accelerated hazards (AH) model's maximum likelihood estimation, log-likelihood, and information criterion. Baseline hazards: NGLL, GLL,KW, EW, MLL, PGW, GG, MKW, Log-logistic, Weibull, Log-normal, Burr-XII, and Gamma

Usage

AHMLE(
  init,
  time,
  delta,
  n,
  basehaz,
  z,
  method = "Nelder-Mead",
  maxit = 1000,
  log = FALSE
)

Arguments

init	: initial points for optimisation
time	: survival times
delta	: vital indicator (0-alive,1 - dead,)
n	: The number of the observations of the data set
basehaz	: baseline hazard structure including baseline (NGLLAH,GLLAH,EWAH,KWAH,MLLAH,PGWAH,GGAH, MKWAH,LLAH,WAH,GAH,LNAH,BXIIAH)
z	: design matrix for covariates (p x n), p >= 1
method	:"nlminb" or a method from "optim"
maxit	:The maximum number of iterations. Defaults to 1000
log	:log scale (TRUE or FALSE)

Format

By default the function calculates the following values:

• AIC: Akaike Information Criterion;

• CAIC: Consistent Akaikes Information Criterion;

• BIC: Bayesian Information Criterion;

• BCAIC: Bozdogan’s Consistent Akaike Information Criterion;

• HQIC: Hannan-Quinn information criterion;

• par: maximum likelihood estimates;

• Value: value of the likelihood function;

• Convergence: 0 indicates successful completion and 1 indicates that the iteration limit maxit.

Details

The function AHMLE returns MLE estimates and information criterion.

Value

a list containing the output of the optimisation (OPT) and the information criterion including (AIC, BIC, CAIC, BCAIC, and HQIC).

Author(s)

Abdisalam Hassan Muse, Samuel Mwalili, Oscar Ngesa, Mutua Kilai, [e-mail]

Examples

#Example #1
data(ipass)
time<-ipass$time
delta<-ipass$status
z<-ipass$arm
AHMLE(init = c(1.0,1.0,1.0,0.5),time = time,delta = delta,n=nrow(z),
basehaz = "GLLAH",z = z,method = "Nelder-Mead",
maxit = 1000)

#Example #2
data(bmt)
time<-bmt$Time
delta<-bmt$Status
z<-bmt$TRT
AHMLE(init = c(1.0,1.0,1.0,0.5),time = time,delta = delta,n=nrow(z),
basehaz = "GLLAH",z = z,method = "Nelder-Mead",
maxit = 1000)

#Example #3
data("e1684")
time<-e1684$FAILTIME
delta<-e1684$FAILCENS
TRT<-e1684$TRT
AGE<-e1684$TRT
z<-as.matrix(cbind(scale(TRT), scale(AGE) ))
AHMLE(init = c(1.0,1.0,1.0,0.5,0.75),time = time,delta = delta,n=nrow(z),
basehaz = "GLLAH",z = z,method = "Nelder-Mead",maxit = 1000)

#Example #4
data("LeukSurv")
time<-LeukSurv$time
delta<-LeukSurv$cens
age<-LeukSurv$age
wbc<-LeukSurv$wbc
tpi<-LeukSurv$tpi
z<-as.matrix(cbind(scale(age), scale(tpi),scale(wbc) ))
AHMLE(init = c(1.0,1.0,1.0,1.0,0.5,0.65,0.85),time = time,delta = delta,n=nrow(z),
basehaz = "NGLLAH",z = z,method = "Nelder-Mead",maxit = 1000)

AHSurv documentation built on June 2, 2022, 5:06 p.m.