mcrp: Multiple criteria risk parity optimization

In bpfaff/mcrp: Multiple criteria risk parity optimization

Description

This function conducts a multiple criteria optimization with respect to the assets' risk contributions of the portfolio higher moments (variance, skewness and kurtosis). The three-element weight vector lambda determines with respect to which higher moments the optimization is conducted. NA entry(ies) in this vector indicate the skipping of a higher moment. That is lambda = c(1, NA, NA) would conduct a pure ERC optimization with respect to the assets' contribution to the portfolio variance.

Usage

mcrp(start, returns, lambda = c(1, 1, 1), ...)

Arguments

start	numeric, a (N x 1) vector of starting values.
returns	matrix, a (T x N) matrix of asset returns.
lambda	numeric, a (3 x 1) weight vector for the partial objectives.
...	ellipsis argument, passed to nlminb().

Value

Object of S4-class PortSol-class.

References

Baitinger, E. and Dragosch, A. and Topalova, A. (2017), Extending the Risk Parity Approach to Higher Moments: Is there Any Value Added?, The Journal of Portfolio Managament, 43(2), 24–36.

Boudt, K. and Peterson, B. and Croux, C. (2008/09), Estimation and decomposition of downside risk for portfolios with non-normal returns, The Journal of Risk, 11(2), Winter 2008/09, 79–103.

Jondeau, E. and Rockinger, M. (2006), Optimal portfolio allocation under higher moments, European Financial Management, 12(1), 29–55.

Examples

data(MultiAsset)
MA <- as.timeSeries(MultiAsset[, 1:4])
r <- na.omit(diff(log(MA)) * 100)
N <- ncol(r)
erc <- mcrp(start = runif(N), returns = r, lambda = c(1, NA, NA), lower = rep(0, N))
w <- Weights(erc)
PortRiskContrib(r, w)

bpfaff/mcrp documentation built on May 13, 2019, 2:24 a.m.