BuyseTest (version 3.3.3)

sensitivity: Sensitivity Analysis for the Choice of the Thresholds

Description

Evaluate a summary statistic (net benefit, win ratio, ...) using GPC along various thresholds of clinical relevance.

Usage

# S4 method for S4BuyseTest
sensitivity(
  object,
  threshold,
  statistic = NULL,
  band = FALSE,
  conf.level = NULL,
  null = NULL,
  transformation = NULL,
  alternative = NULL,
  adj.p.value = FALSE,
  trace = TRUE,
  cpus = 1,
  ...
)

Value

An S3 object of class S3sensitivity.

Arguments

object

an R object of class S4BuyseTest, i.e., output of BuyseTest

threshold

[list] a list containing for each endpoint the thresholds to be considered.

statistic

[character] the statistic summarizing the pairwise comparison: "netBenefit", "winRatio", "favorable", "unfavorable". See the documentation of the coef method for further details. Default value read from BuyseTest.options().

band

[logical] should simulateneous confidence intervals be computed?

conf.level

[numeric] confidence level for the confidence intervals. Default value read from BuyseTest.options().

null

[numeric] right hand side of the null hypothesis (used for the computation of the p-value).

transformation

[logical] should the CI be computed on the logit scale / log scale for the net benefit / win ratio and backtransformed. Otherwise they are computed without any transformation. Default value read from BuyseTest.options(). Not relevant when using permutations or percentile bootstrap.

alternative

[character] the type of alternative hypothesis: "two.sided", "greater", or "less". Default value read from BuyseTest.options().

adj.p.value

[logical] should p-value adjusted for multiple comparisons be computed?

trace

[logical] Should the execution of the function be traced?

cpus

[integer, >0] the number of CPU to use. Default value is 1.

...

argument passsed to the function transformCIBP of the riskRegression package.

Details

Simulateneous confidence intervals and adjusted p-values are computed using a single-step max-test approach via the function transformCIBP of the riskRegression package.

Examples

if (FALSE) {
require(ggplot2)

## simulate data
set.seed(10)
df.data <- simBuyseTest(1e2, n.strata = 2)

## with one endpoint
ff1 <- treatment ~ TTE(eventtime, status = status, threshold = 0.1)
BT1 <- BuyseTest(ff1, data= df.data)
se.BT1 <- sensitivity(BT1, threshold = seq(0,2,0.25), band = TRUE)
plot(se.BT1)

## with two endpoints
ff2 <- update(ff1, .~. + cont(score, threshold = 1))
BT2 <- BuyseTest(ff2, data= df.data)
se.BT2 <- sensitivity(BT2, threshold = list(eventtime = seq(0,2,0.25), score = 0:2),
                      band = TRUE)
plot(se.BT2)
plot(se.BT2, col = NA)
}