MAE: Mean Absolute Error

In StatPerMeCo: Statistical Performance Measures to Evaluate Covariance Matrix Estimates

Description

Compute the Mean Absolute Error between the matrices S and H. See, Becker et al.(2015).

Usage

MAE(S, H)

Arguments

S	Proxy for the conditional covariance/correlation matrix
H	Estimate of the conditional covariance/correlation matrix.

Author(s)

Carlos Trucios

References

Becker, R., Clements, A. E., Doolan, M. B., & Hurn, A. S. (2015). Selecting volatility forecasting models for portfolio allocation purposes. International Journal of Forecasting, 31(3), 849-861.

Examples

X = matrix(rnorm(4000),ncol=4)
S = diag(4)
H = cov(X)

MAE(S, H)

Example output

[1] 0.02497009

StatPerMeCo documentation built on May 2, 2019, 12:21 p.m.