Skip to contents

Generates an upside value at risk (VaR) quantile based on the Upper Partial Moment ratio.

Usage

UPM.VaR(percentile, degree, x)

Arguments

percentile

numeric [0, 1]; The percentile for right-tail VaR.

degree

integer; (degree = 0) gives the interpolated empirical quantile (quantile(x, 1 - percentile, type = 7)), which on tied data need not be an exact inverse of UPM.ratio(0, ., x). Use it for probability statements. (degree = 1) gives an area-weighted (severity-weighted) threshold, the (1 - percentile)-expectile of x (Newey and Powell 1987): percentile of the area of deviations, not of the observations, lies above it, so it is not a quantile of x. Higher degrees weight large deviations more.

x

a numeric vector.

Value

Returns the type-7 empirical quantile (degree = 0), whose strict or inclusive sample tail fraction may differ from percentile because of interpolation or ties, or the threshold with percentile of the directional deviation area above it (degree > 0).

References

Viole, F. and Nawrocki, D. (2013) "Nonlinear Nonparametric Statistics: Using Partial Moments" (ISBN: 1490523995, 2nd edition: https://ovvo-financial.github.io/NNS/book/)

Author

Fred Viole, OVVO Financial Systems

Examples

set.seed(123)
x <- rnorm(100)

## For 5th percentile, right-tail
UPM.VaR(0.05, 0, x)
#>      95% 
#> 1.566526