confint.SCREENING: Peer-bootstrap sensitivity intervals for the peer performance...

In PeerPerformance: Luck-Corrected Peer Performance Analysis in R

Peer-bootstrap sensitivity intervals for the peer performance ratios

Description

Computes peer-bootstrap sensitivity intervals for one of the peer performance ratios (\hat\pi^+, \hat\pi^0, or \hat\pi^-) of a SCREENING object, by a nonparametric peer (pairwise) bootstrap: for each focal fund its peers are resampled with replacement and the ratio is recomputed from the stored pairwise p-values and test statistics. The interval therefore reflects the peer-composition and aggregation uncertainty, holding the individual pairwise test statistics and the selected \lambda fixed. It does not include return-sampling or \lambda-selection uncertainty and should not be interpreted as a confidence interval with nominal coverage for the underlying population ratio.

Usage

## S3 method for class 'SCREENING'
confint(
  object,
  parm = c("pipos", "pizero", "pineg"),
  level = 0.95,
  ...,
  nBoot = 499L,
  gammaPos = NULL,
  gammaNeg = NULL
)

Arguments

object	A SCREENING object (within-group or cross-group; not screen_beta).
parm	Which ratio to bound: "pipos" (default), "pizero", or "pineg".
level	Central peer-bootstrap interval level. Default: 0.95.
...	Unused.
nBoot	Number of bootstrap resamples. Default: 499.
gammaPos, gammaNeg	One-sided thresholds used to recompute the ratios (should match those of the original screening). By default, the values are taken from object; for older objects the fallbacks are 0.4 and 0.6.

Value

A matrix with one row per fund and two columns (lower and upper bounds); the point estimate is attached as attribute "estimate".

Author(s)

David Ardia and Kris Boudt.

See Also

alphaScreening.

Examples

data("hfdata")
set.seed(1234)
sc <- alphaScreening(hfdata[, 1:15], control = list(nCore = 1))
confint(sc, parm = "pipos")

PeerPerformance documentation built on Oct. 15, 2026, 1:06 a.m.