InformationAdjustedCorr: Information Adjusted Correlation

In Trading: CCR, Advanced Correlation & Beta Estimates, Betting Strategies

Information Adjusted Correlation

Description

Calculates the Information-Adjusted Correlation between the track records of various assets/strategies which covers for cases whereby the 'typical' Pearson's correlation assumptions do not hold. The normalized cross sample entropy has been utilized for the mutual information estimation.

Usage

InformationAdjustedCorr(x, y, m = 2, r = 0.2)

Arguments

x	a vector containing the track record of the underlying asset/strategy (can be a data.table, data.frame, vector etc)
y	a vector containing the track record of the underlying asset/strategy (can be a data.table, data.frame, vector etc)
m	an integer value defining the embedding dimension for the sample entropy calculation, default value is 2
r	a double value defining the tolerance for the sample entropy calculation, default value is 0.2

Value

The information adjusted correlation

Author(s)

Tasos Grivas <[e-mail]>

References

https://github.com/devisechain/Devise/blob/master/yellow_paper.pdf

Examples

x = PerformanceAnalytics::edhec[,c("Short Selling")]
y = PerformanceAnalytics::edhec[,c("Convertible Arbitrage")]
Information_Adjusted_Corr = InformationAdjustedCorr(x, y, m=2, r=0.2)

Trading documentation built on Feb. 13, 2024, 3 a.m.