glrt { New R Package for Analyzing Interval-Censored Survival Data - Interval-Censored-Time-to-Event Data: Methods and Applications - page 392

[1,]3.215846

$df

[1]1

$p

[,1]

[1,]0.0729285

Because the data have exactly observed observations, gLRT2 does not ap-

ply. Based on the test results above, the difference between the two survival

functions of the gender groups is only mildly significant. Note that, as men-

tioned in Zhao et al. (2008), choice of rho and gamma may aect the test
results.

14.4.2 Estimating the Survival Function

Using the data cosmesis with the treatment indicator dropped, we can obtain
the survival function estimate based on the combined data from both treat-

ment groups. Note that the function ModifiedEMICM is a debugged version of
the function EMICM in the package Icens and returns through sigma the MLE
of the distribution function by default.

>data(cosmesis)

>dim(cosmesis)

[1]943
>1-signif(ModifiedEMICM(cosmesis[,1:2])$sigma,3)

(4,5](6,7](7,8](8,9](10,11](11,12](12,13]

0.95510.93250.87600.87600.87600.79700.7970

(13,14](14,15](15,16](16,17](17,18](18,19](19,20]

0.79700.79700.79700.73700.73700.71500.5710

(21,22](22,23](23,24](24,25](25,26](26,27](27,30]

0.57100.57100.57100.52100.52100.52100.5210

(30,31](31,32](33,34](34,35](35,36](36,37](38,39]