README.md

In Alanocallaghan/surverify: Calculation of survival concordance measures.

surverify

The goal of surverify is to implement concordance statistics in R using modern package development tools (one might even say "in a tidy way", though I would elect not to).

Installation

Install from github with

install_github("Alanocallaghan/surverify")

Here's a demo showing I calculate Uno's C correctly.

load_all()
#> Loading surverify
#> 
#> Attaching package: 'testthat'
#> The following object is masked from 'package:devtools':
#> 
#>     test_file
library("survival")
library("survAUC")

TR <- ovarian[1:16,]
TE <- ovarian[17:26,]
train.fit  <- coxph(
    Surv(futime, fustat) ~ age,
    x = TRUE, 
    y = TRUE,
    method = "breslow",
    data = TR
)

lpnew <- predict(train.fit, newdata = TE)
#> 
#> Attaching package: 'stats'
#> The following object is masked from 'package:surverify':
#> 
#>     stepfun
Surv.rsp <- Surv(TR$futime, TR$fustat)
Surv.rsp.new <- Surv(TE$futime, TE$fustat)

Cstat <- UnoC(Surv.rsp, Surv.rsp.new, lpnew)

cme <- uno_c(Surv.rsp, Surv.rsp.new, lpnew)
Cstat
#> [1] 0.7333333
cme
#> [1] 0.7333333

Alanocallaghan/surverify documentation built on June 24, 2021, 11:01 a.m.