S4BuyseTest-coef: Coef Method for Class "S4BuyseTest"

In BuyseTest: Generalized Pairwise Comparisons

Coef Method for Class "S4BuyseTest"

Description

Extract summary statistics from the result of a BuyseTest function.

Usage

## S4 method for signature 'S4BuyseTest'
coef(
  object,
  endpoint = NULL,
  statistic = NULL,
  stratified = FALSE,
  cumulative = NULL,
  resampling = FALSE,
  ...
)

Arguments

object	output of BuyseTest
endpoint	[character] for which endpoint(s) the summary statistic should be output? If NULL returns the summary statistic for all endpoints.
statistic	[character] the type of summary statistic. See the detail section.
stratified	[logical] should the summary statistic be strata-specific? Otherwise a summary statistic over all strata is returned.
cumulative	[logical] should the summary statistic be cumulated over endpoints? Otherwise display the contribution of each endpoint.
resampling	[logical] should the summary statistic obtained by resampling be output?
...	ignored.

Details

One of the following statistic can be specified:

• "netBenefit": returns the net benefit.

• "winRatio": returns the win ratio.

• "favorable": returns the proportion in favor of the treatment (also called Mann-Whitney parameter).

• "unfavorable": returns the proportion in favor of the control.

• "unfavorable": returns the proportion of neutral pairs.

• "unfavorable": returns the proportion of uninformative pairs.

• "count.favorable": returns the number of pairs in favor of the treatment.

• "count.unfavorable": returns the number of pairs in favor of the control.

• "count.neutral": returns the number of neutral pairs.

• "count.uninf": returns the number of uninformative pairs.

Value

When resampling=FALSE and stratified=FALSE, return a numeric vector. When resampling=FALSE and stratified=TRUE, return a matrix. When resampling=TRUE and stratified=FALSE, return a matrix. When resampling=TRUE and stratified=TRUE, return an 3-dimensional array.

Author(s)

Brice Ozenne

BuyseTest documentation built on March 31, 2023, 6:55 p.m.