TM2: Tau-Restricted Mean Survival

In umich-biostatistics/corrsurv: Two-Sample Tests for Correlated Survival Endpoints

Description

Estimate the tau-restricted mean survival across multiple follow-up intervals.

Usage

TM2(X, delta, Tau, t, var_output = "proposed")

Arguments

X	follow-up time of right censored data (values must be geq 0)
delta	status indicator, 0=alive, 1=dead. (values must be 0,1)
Tau	upper limit of integration (cannot be greater than largest follow-up time, cannot be negative)
t	start times of follow-up windows (default=seq(from=0, to=A-Tau,by=(A-Tau)/(b-1)), must be of length b if both specified, largest value cannot be greater than A-Tau, no repeats)
var_output	Type of variance estimator. Options are c("proposed","independence", "sandwich","all")

Details

Estimate the tau-restricted mean survival as described in Tayob, N. and Murray, S., 2016. Nonparametric restricted mean analysis across multiple follow-up intervals. Statistics & probability letters, 109, pp.152-158.

Value

A list object which contains

• Mean - vector containing sample estimates of overall tau-restricted mean survival in each group

• Var - vector containing empirical variance of estimates of overall tau-restricted mean survival in each group

• test_stat - test statistic of two-sample test

• test_stat_p - p-value of two-sample test

Author(s)

Nabihah Tayob

References

Tayob, N. and Murray, S., 2016. Nonparametric restricted mean analysis across multiple follow-up intervals. Statistics & probability letters, 109, pp.152-158.

Examples

data("TM2data")

output = TM2(X = TM2data$X, delta = TM2data$delta, Tau = 12, 
             t = seq(from = 0, to = 24, by = 6), var_output = "all")
summary(output)
plot(output)

output = TM2(X = TM2data$X, delta = TM2data$delta, Tau = 12, 
             t = seq(from = 0, to = 24, by = 6))
summary(output)
plot(output)

output = TM2(X = TM2data$X, delta = TM2data$delta, Tau = 12, 
             t = seq(from = 0, to = 24, by = 6), var_output = "independence")
summary(output)
plot(output)

output = TM2(X = TM2data$X, delta = TM2data$delta, Tau = 12, 
             t = seq(from = 0, to = 24, by = 6), var_output = "sandwich")
summary(output)
plot(output)

umich-biostatistics/corrsurv documentation built on Jan. 11, 2020, 2:03 a.m.