Skip to content

tbeason/AsymmetricRisk.jl

master
Switch branches/tags
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
src
 
 
 
 
 
 
 
 
 
 
 
 
 
 

AsymmetricRisk.jl

This package is currently under development.

Build Status codecov.io

Traditional measures of risk, such as the variance of a time series or the covariance between two time series, use all available data points (aka information) when computing the statistical measure. However, it is becoming common to consider separately the notions of "upside" and "downside" risks. For example, a large literature has documented that people fear losses more than they like gains of similar magnitude. This package contains implementations of several asymmetric risk measures that have been published in financial and economics research.

Univariate measures:

  • Variance-based (semi-variance)
  • Lower partial moments (Harlow 1991)
  • VaR-based (Expected Shortfall / Expected Longrise)

Bivariate measures:

  • Correlation-based (Ang & Chen 2001 + statistical test of Hong, Tu, & Zhou 2007 + one-sided as in Schreindorfer 2019)
  • Beta-based (Ang, Chen, & Xing 2006)
  • Entropy-based (Jiang, Wu, & Zhou 2018)
  • Coskewness (Harvey & Siddique 2000)
  • Quantile dependence

Usage

From the Julia REPL type

]add https://github.com/tbeason/AsymmetricRisk.jl

which will clone the repository.

You can then use the package by typing

using AsymmetricRisk

See the docs for more information.

About

A Julia package for computing asymmetric risk measures on univariate and bivariate data.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages