Luck-Corrected Peer Performance Analysis in R

Provides functions to perform the peer performance analysis of funds' returns as described in Ardia and Boudt (2018) .

PeerPerformance (Ardia and Boudt, 20xx) is an R package for the peer-performance evaluation of financial investments with luck-correction. In particular, it implements the peer performance ratios of Ardia and Boudt (2018) which measure the percentage of peers a focal fund outperforms and underperforms, after correction for luck. It is useful for fund or portfolio managers to benchmark their investments or screen a universe of new funds. In addition, it implements the testing framework for the Sharpe and modified Sharpe ratios, described in Ledoit and Wolf (2008) and Ardia and Boudt (2015).

The latest stable version of PeerPerformance is available at https://cran.r-project.org/package=PeerPerformance.

The latest development version of PeerPerformance is available at https://github.com/ArdiaD/PeerPerformance.

Please cite PeerPerformance in publications.

Ardia, D., Boudt, K. (2015). Testing equality of modified Sharpe ratios.
Finance Research Letters 13, pp.97-104.
http://dx.doi.org/10.1016/j.frl.2015.02.008
http://dx.doi.org/10.2139/ssrn.2516591

Ardia, D., Boudt, K. (2018).
The peer performance ratios of hedge funds_.
Journal of Banking and Finance 87, pp.351-368.
http://dx.doi.org/10.1016/j.jbankfin.2017.10.014
http://dx.doi.org/10.2139/ssrn.2000901

Ardia, D., Boudt, K. (20xx).
PeerPerformance: Luck-corrected peer performance analysis in R.
R package.
https://github.com/ArdiaD/PeerPerformance

Ledoit, O., Wolf, M. (2008).
Robust performance hypothesis testing with the Sharpe ratio.
Journal of Empirical Finance 15(5), pp.850-859.
http://dx.doi.org/10.1016/j.jempfin.2008.03.002

News

Changes in Version 2.2.1 (DA) o switch to parallel package o references updated

Changes in Version 2.1.4 (DA) o small fix in counting NA

Changes in Version 2.1.3 (DA) o documentation fixes

Changes in Version 2.1.2 (DA) o documentation fixes

Changes in Version 2.1.1 (DA) o documentation fixes o first CRAN release

Changes in Version 2.1.00 (DA) o New PeerPerformance documentation o compiler imported directly within function

Changes in version 2.0.11 (DA) o Examples added o Block length not exported anymore

Changes in version 2.0.10 (DA) o Roxygen documentation o testthat added o format of code

Changes in version 2.0.9 (DA) o Update CITATION and DESCRIPTION

Changes in version 2.0.8 (DA) o Small improvements with compiler o Citations updated

Changes in version 2.0.6 and 2.0.7 (DA) o Various improvements o Small fix in documentation

Changes in Version 2.0.5 (DA) o Fix in documentation for modified Sharpe testing o Small fix in pvalue computation by bootstrap (symmetric)

Changes in Version 2.0.4 (DA) o Bug fix for alpha screening when NA are in the dataset o Risk-free rate removed o Tstat used for attribution

Changes in Version 2.0.3 (DA) o Major functions contain risk-free rates (zero by default) o Documentation updated o Adjustement factor robustified

Changes in Version 2.0.2 (DA) o alphaScreening fixed o alphaScreening now encompasses hac estimation with sandwich and lmtest o citation file updated

Changes in Version 2.0.1 (DA) o new package's name o new package's number o new package's structure

Changes in Version 1-00.15 (DA) o pi+ fixed o default settings for lambda = NULL

Changes in Version 1-00.14 (DA) o fix of errors in examples

Changes in Version 1-00.13 (DA) o control parameters for lambda data driven (NULL) o documentation updated o function for optimal lambda corrected and enhanced o funcion pizero and pi corrected

Changes in Version 1-00.12 (DA) o attribution proportions corrected o computation of pi0 now accounts for NA in pvalues (in msharpe with na.rm = FALSE) o new data set (randomized data) added

Changes in Version 1-00.11 (DA) o functions for computing the standard deviation based on the delta rule are now coded outside and therefore accessible o optimal block length added for sharpe and modified sharpe with documentation

Changes in Version 1-00.10 (DA) o bootstrap p-value consistent with Barras et al. o control ttype = 1, or = 2, indicating if based on ratio or product o control ptype = 1, or = 2, indicating of pvalue based on symmetric or asymmetric version of bootstrap o several speedup

Changes in Version 1-00.09 (DA) o simplification of boostrap functions for Sharpe and modified Sharpe

Changes in Version 1-00.08 (DA) o various fixes/improvements based on codetools package's outputs

Changes in Version 1-00.07 (DA) o modified Sharpe ratio set to NA whenever the modified VaR is negative o function sharpe added o function msharpe added o other functions modified to rely on sharpe and msharpe functions o documentation modified with X instead of rdata o removed default values for subfunctions to avoid wrong defaults

Changes in Version 1-00.06 (DA) o change of data; now using the reconstructed database of HFR

Changes in Version 1-00.05 (DA) o hac estimator modified in mSharpe testing; now bounded to T

Changes in Version 1-00.04 (DA) o modified Sharpe ratio testing and screening added o documentation modified

Changes in Version 1-00.03 (DA) o circular bootstrap with user-defined block length added o boostrap relies on random integers instead of uniform numbers o documentation modified o enhancement of functions descriptions

Changes in Version 1-00.02 (DA) o hac estimator added to sharpeTesting and sharpeScreening o hac studentized bootstrap estimator added to sharpeTesting and sharpeScreening o documentation modified o package and paper presented to the R/Finance conference 2012; see http://www.rinfinance.com/

Changes in Version 1-00.01 (DA) o first release o package includes (parallel) alpha and sharpe screening algorithms