Generalized Correlations and Initial Causal Path

Since causal paths from data are important for all sciences, the package provides sophisticated functions. The idea is simply that if X causes Y (path: X to Y) then non-deterministic variation in X is more "original or independent" than similar variation in Y. Since causal variables are also exogenous in a model, we provide new exogeneity tests. We compare two flipped kernel regressions: X=f(Y, Z) and Y=g(X,Z), where Z are control variables. Our first two criteria compare absolute cross products of regressor values and residuals (Cr1) and absolute residuals (Cr2), are both quantified by stochastic dominance of four orders (SD1 to SD4). Our third criterion (Cr3) expects X to be better able to predict Y than the other way around using generalized partial correlation If |r*(x|y,z)|> |r*(y|x,z)| it suggests that y is more likely the "kernel cause" of x. The usual partial correlations are generalized with a new non-symmetric matrix developed here. Partial correlations help asses effect of x on y after removing the effect of a set of variables. The package provides additional tools for causal assessment, for printing the causal directions in a clear, comprehensive compact summary form, for matrix algebra, for "outlier detection", and for numerical integration by the trapezoidal rule, stochastic dominance, etc. The package has functions for bootstrap-based statistical inference.


News

Package: generalCorr

Version 1.1.2 [2018-07-11] o Added parcorMtx function to compute partial correlation matrices and some bootstrap summarizing bootSignPcent using -100 to 100 range, and some bug fixes.

Version 1.1.1 [2018-01-24] o improvements to vignette2, option to use older Cr1 criterion and some bootstrap summarizing functions added.

Version 1.1.0 [2018-01-04] o revised first criterion Cr1 to directly reflect orthogonality between regressors and errors, leading to many changes.

Version 1.0.9 [2017-10-03] o further revised parcor_ijk and revised versions of 3 vignettes

Version 1.0.9 [2017-09-05] o further minor corrections

Version 1.0.7 [2017-09-02] o slightly revised parcor_ijk and inclusion of 3 vignettes

Version 1.0.6 [2017-07-21] o New functions added descriptions updated especially silentMtx

Version 1.0.5 [2017-06-16] o New functions added descriptions updated especially silentMtx

Version 1.0.4 [2017-06-08] o New functions added and descriptions updated especially causeSummary for strength index for unanimity of three criteria in [-100, 100] range.

Version 1.0.3 [2016-06-28] o New functions added for bootstrap and causal path assessment without much printing.

Version: 1.0.2 [2016-05-20] o New functions added to treat some variables as control variables, not part of causal paths.

Version: 1.0.1 [2016-05-20] o cosmetic changes to many functions, changed output titles in somePairs(), some0Pairs(), allPairs() with added example in parcor_ridg()

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.

install.packages("generalCorr")

1.1.2 by H. D. Vinod, 5 months ago


Browse source code at https://github.com/cran/generalCorr


Authors: Prof. H. D. Vinod , Fordham University , NY.


Documentation:   PDF Manual  


GPL (>= 2) license


Depends on np, xtable, meboot, psych

Suggests R.rsp


See at CRAN