targetPeerPerformance: Targeted peer-performance screening for selected funds

Description

Performs peer-performance screening for a user-selected subset of funds (the “focal” funds) against the whole universe, returning detailed outputs for those focal funds only. It is a convenience wrapper that calls the corresponding screening function with the cross-group argument Y set to the full matrix X; equivalently, targetPeerPerformance(X, funds, "alpha") is alphaScreening(X[, funds], Y = X).

Usage

targetPeerPerformance(
  X,
  funds,
  method = c("alpha", "sharpe", "msharpe"),
  factors = NULL,
  level = 0.9,
  na.neg = TRUE,
  control = list()
)

Value

A SCREENING object (see alphaScreening) whose fund-level components (pizero, pipos, pineg, the performance measure, npeer, ...) cover the focal funds only, and whose pval/tstat/difference matrices have one row per focal fund and one column per universe fund. Works with the print, plot, summary, and as.data.frame methods.

Arguments

X: Matrix \((T \times N)\) of \(T\) returns for \(N\) funds. NA values are allowed.
funds: Integer indices or character column names identifying the focal funds. The output preserves the order provided in funds.
method: Screening method: "alpha" (default), "sharpe", or "msharpe".
factors: Optional matrix of factor returns (only when method = "alpha").
level: Modified Value-at-Risk level (only when method = "msharpe").
na.neg: Logical; return NA for a negative modified Value-at-Risk (only when method = "msharpe").
control: Control parameters (see alphaScreening).

Author

Murilo Andre Peres Pereira, David Ardia and Kris Boudt.

Examples

Run this code

data("hfdata")
rets <- hfdata[, 1:10]

## focal Sharpe screening (funds by index) against the whole universe
out <- targetPeerPerformance(rets, funds = c(2, 5, 7), method = "sharpe",
                             control = list(nCore = 1))
out$sharpe