Generalized Correlations and Kernel Causality Using R Package GeneralCorr

38 Pages Posted: 21 May 2016

See all articles by Hrishikesh D. Vinod

Hrishikesh D. Vinod

Fordham University - Department of Economics

Date Written: May 19, 2016

Abstract

Karl Pearson developed the correlation coefficient r(X,Y) in 1890's. Vinod (2014) develops new generalized correlation coefficients so that when r*(Y|X) > r*(X|Y) then X is the "kernel cause" of Y. Vinod (2015a) argues that kernel causality amounts to model selection between two kernel regressions, E(Y|X) = g1(X) and E(X|Y) = g2(Y) and reports simulations favoring kernel causality. An R software package called 'generalCorr' computes generalized correlations, partial correlations and plausible causal paths. This paper describes various R functions in the package, using examples to describe them. We are proposing an alternative quantfication to extensive causality apparatus of Pearl (2010) and additive-noise type methods in Mooij et al. (2014), who seem to offer no R implementations. My methods applied to certain public benchmark data report a 70-75% success rate. We also describe how to use the package to assess endogeneity of regressors.

Keywords: generalized measure of correlation, non-parametric regression, partial correlation, observational data, endogeneity

JEL Classification: C10, C14, C87, E52

Suggested Citation

Vinod, Hrishikesh D., Generalized Correlations and Kernel Causality Using R Package GeneralCorr (May 19, 2016). Available at SSRN: https://ssrn.com/abstract=2782223 or http://dx.doi.org/10.2139/ssrn.2782223

Hrishikesh D. Vinod (Contact Author)

Fordham University - Department of Economics ( email )

Dealy Hall
Bronx, NY 10458
United States
718-817-4065 (Phone)
718-817-3518 (Fax)

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
178
Abstract Views
1,070
Rank
305,000
PlumX Metrics