Plot method for the SCREENING object returned by
alphaScreening, sharpeScreening and
msharpeScreening. It reproduces the peer performance
screening plot of Ardia and Boudt (2018): funds are sorted by their
performance measure and, for each fund, the estimated outperformance
(\(\hat\pi^+\)), equal-performance (\(\hat\pi^0\)) and underperformance
(\(\hat\pi^-\)) ratios are displayed as a horizontal stacked bar. The
dashed diagonal lines depict the naive percentile-rank benchmark
(\(\hat\pi^0 = 0\)); the gap between the black \(\hat\pi^+\) area and the
diagonal visualizes the luck correction.
# S3 method for SCREENING
plot(
x,
nblock = NULL,
reference = NULL,
band = 27.5,
colorset = c(grDevices::gray(0), grDevices::gray(0.8), grDevices::gray(0.5)),
...
)Invisibly returns the (sorted, possibly aggregated) matrix of ratios that is plotted.
A SCREENING object.
Optional number of equally-sized blocks into which the funds
(sorted by performance) are aggregated by averaging, as in Ardia and Boudt
(2018). Default: nblock = NULL, i.e. one bar per fund.
A logical value indicating whether the dashed
percentile-rank reference lines should be drawn. Default:
reference = NULL, i.e. drawn for within-group screening and omitted
for cross-group (Y-based) screening, where the within-group
percentile-rank benchmark does not apply. A single focal fund (cross-group
with one fund in X) is shown as a single stacked bar.
Half-width (in percentage points) of the reference band drawn
around the central diagonal. Default: band = 27.5.
Vector of three colors for the \(\hat\pi^+\),
\(\hat\pi^0\) and \(\hat\pi^-\) areas. Default:
c(gray(0), gray(0.8), gray(0.5)).
Further graphical arguments passed to barplot.
David Ardia and Kris Boudt.
If the screening was run with screen_beta = TRUE, the alpha
(first) coefficient is used.
Ardia, D., Boudt, K. (2018). The peer performance ratios of hedge funds. Journal of Banking and Finance 87, pp.351--368. tools:::Rd_expr_doi("10.1016/j.jbankfin.2017.10.014")
alphaScreening, sharpeScreening and
msharpeScreening.
# \donttest{
data("hfdata")
set.seed(1234)
sc <- alphaScreening(hfdata[, 1:30], control = list(nCore = 1))
plot(sc)
# }
Run the code above in your browser using DataLab