S4BuyseTest-vcov: Extract Uncertainty from GPC

In BuyseTest: Generalized Pairwise Comparisons

Extract Uncertainty from GPC

Description

Extract uncertainty about the summary statistics (net benefit, win ratio, ...) from GPC.

Usage

## S4 method for signature 'S4BuyseTest'
vcov(
  object,
  endpoint = NULL,
  statistic = NULL,
  strata = FALSE,
  cumulative = TRUE,
  ...
)

Arguments

object	a S4BuyseTest object, output of BuyseTest.
endpoint	[character] for which endpoint(s) the variance-covariance matrix should be output? If NULL consider all endpoints.
statistic	[character] the statistic summarizing the pairwise comparison relative to which the variance is to be output: "netBenefit", "winRatio", "favorable", "unfavorable". See the documentation of the coef method for further details. Default value read from BuyseTest.options().
strata	[character vector] the strata relative to which the variance-covariance matrix should be output. Can also be "global" or FALSE to output the statistic pooled over all strata.
cumulative	[logical] should the summary statistic be cumulated over endpoints? Otherwise display the contribution of each endpoint.
...	ignored.

Details

When consider a second order H-decomposition, it is only used to estimate variance: the correlation between endpoints is evaluated using the first order H-decomposition.

Value

A numeric matrix.

Author(s)

Brice Ozenne

BuyseTest documentation built on Aug. 8, 2025, 6:32 p.m.