Learn R Programming

⚠️There's a newer version (1.2.6) of this package.Take me there.

generalCorr (version 1.2.1)

Generalized Correlations, Causal Paths and Portfolio Selection

Description

Since causal paths from data are important for all sciences, the package provides many sophisticated functions. causeSummBlk() gives easy-to-interpret causal paths. Let Z denote control variables and compare two flipped kernel regressions: X=f(Y, Z)+e1 and Y=g(X,Z)+e2. Our criterion Cr1 says that if |e1*Y|>|e2*X| then variation in X is more "exogenous or independent" than in Y and causal path is X to Y. Criterion Cr2 requires |e2|<|e1|. These inequalities between many absolute values are quantified by four orders of stochastic dominance. Our third criterion Cr3 for the causal path X to Y requires new generalized partial correlations to satisfy |r*(x|y,z)|< |r*(y|x,z)|. The function parcorVec() reports generalized partials between the first variable and all others. The package provides several R functions including get0outliers() for outlier detection, bigfp() for numerical integration by the trapezoidal rule, stochdom2() for stochastic dominance, pillar3D() for 3D charts, canonRho() for generalized canonical correlations, depMeas() measures nonlinear dependence, and causeSummary(mtx) reports summary of causal paths among matrix columns is easiest to use. Portfolio selection: decileVote(), momentVote(), dif4mtx(), exactSdMtx() can rank several stocks. Several functions whose names begin with 'boot' provide bootstrap statistical inference including a new bootGcRsq() test for "Granger-causality" allowing nonlinear relations. See five vignettes of the package for theory and usage tips. See Vinod (2019) \doi{10.1080/03610918.2015.1122048}.

Copy Link

Version

Install

install.packages('generalCorr')

Monthly Downloads

249

Version

1.2.1

License

GPL (>= 2)

Maintainer

Hrishikesh Vinod

Last Published

December 8th, 2021

Functions in generalCorr (1.2.1)

Function for computing a vector of one-lagged values of xj, a variable from panel data.

Granger nonlinear causality R^2 for x1=f(x1,x2), R^2 for flipped x1 and x2 and the difference between the two R^2 values

Function to compute a vector of 2 lagged values of a variable from panel data.

Nonlinear Granger causality between two time series workhorse function.(local constant version)

Granger nonlinear causality R^2 for x1=f(x1,x2) minus R^2 for flipped 1 and 2

Nonlinear Granger causality between two time series workhorse function.

Compute fitted values from kernel regression of x on y and y on x

Block version of abs-stdres Absolute values of residuals of kernel regressions of standardized x on standardized y, no control variables.

European Crime Data

Block version of Absolute values of residuals of kernel regressions of standardized x on standardized y and control variables.

Absolute values of residuals of kernel regressions of x on y when both x and y are standardized.

Compute usual summary stats of 'sum' indexes from bootPairs output

Absolute residuals of kernel regression of x on y.

Probability of unambiguously correct (+ or -) sign from bootPairs output transformed to percentages.

Block version abs_stdrhser Absolute residuals kernel regressions of standardized x on y and control variables, Cr1 has abs(Resid*RHS).

Compute vector of n999 nonlinear Granger causality paths

Report causal identification for all pairs of variables in a matrix (deprecated function). It is better to choose a target variable and pair it with all others, instead of considering all possible targets.

internal badCol

Compute vector of n999 nonlinear Granger causality paths

Absolute residuals kernel regressions of standardized x on y and control variables, Cr1 has abs(RHS*y) not gradients.

Absolute values of Hausman-Wu null in kernel regressions of x on y when both x and y are standardized.

Generalized canonical correlation, estimating alpha, beta, rho.

All Pair Version Kernel (block) causality summary paths from three criteria

Internal diff.e0

Absolute values of residuals of kernel regressions of x on y when both x and y are standardized and control variables are present (C for control presence).

internal da2Lag

Two sequences: starting+ending values from n and blocksize (internal use)

Block Version Kernel causality summary causal paths from three criteria

bootstrap confidence intervals for exact stochastic dominance SD1 to SD4.

Function compares nine deciles of a matrix to reference minimum (eg p stock returns)

Compute the numerical integration by the trapezoidal rule.

No print (NoP) version of causeSummBlk summary causal paths from three criteria

compute the matrix R* of generalized correlation coefficients.

Matrix R* of generalized correlation coefficients captures nonlinearities using blocks.

depMeas Signed measure of nonlinear nonparametric dependence between two vectors.

Probability of unambiguously correct (+ or -) sign from bootPairs output

Compute confidence intervals [quantile(s)] of indexes from bootPairs output

After removing control variables, magnitude of effect of x on y, and of y on x.

Function to do pairwise deletion of missing rows.

Kernel regression with options for residuals and gradients.

Function compares Pearson Stats and Sharpe Ratio for a matrix of stock returns

Function to do compute the minor of a matrix defined by row r and column c.

Function to do matched deletion of missing rows from x, y and z variable(s).

internal min.e0

Function to do matched deletion of missing rows from x, y and control variable(s).

Matrix of generalized partial correlation coefficients, always leaving out control variables, if any.

Compute cofactor of a matrix based on row r and column c.

Vector of hybrid generalized partial correlation coefficients, hybrid version of parcorVec subtracting only linear effects but using generlized correlation between OLS residuals

Vector of generalized partial correlation coefficients (GPCC), always leaving out control variables, if any.

Absolute values of gradients (apd's) of kernel regressions of x on y when both x and y are standardized.

Absolute values of gradients (apd's) of kernel regressions of x on y when both x and y are standardized and control variables are present.

Compute matrix of n999 rows and p-1 columns of bootstrap `sum' index (strength from older criterion Cr1, with newer Cr2 and Cr3).

Compute matrix of n999 rows and p-1 columns of bootstrap `sum' (strength from Cr1 to Cr3).

internal ridgek

Silently compute generalized (ridge-adjusted) partial correlation coefficients from matrix R*.

Block version of generalized partial correlation coefficients between Xi and Xj, after removing the effect of xk, via nonparametric regression residuals.

generalCorrInfo

generalCorr package description:

Kernel causality summary of evidence for causal paths from three criteria

sudoCoefParcorH

Peudo regression coefficients from hybrid generalized partial correlation coefficients (HGPCC).

internal rijMrji

Compute ranks of rows of matrix and summarize them into a choice suggestion.

Kernel regression with control variables and optional residuals and gradients.

Approximate overall magnitudes of kernel regression partials dx/dy and dy/dx.

Exact stochastic dominance computation from areas above ECDFs compared to common reference minimum (refmin) for order SD1 to SD4

Matrix R* of generalized correlation coefficients captures nonlinearities.

Compares two vectors (portfolios) using stochastic dominance of orders 1 to 4.

Generalized partial correlation coefficients between Xi and Xj, after removing the effect of Xk, via OLS regression residuals.

Older Kernel causality summary of evidence for causal paths from three criteria

Function to compute outliers and their count using Tukey method using 1.5 times interquartile range (IQR) to define boundaries.

Kernel regression with control variables and optional residuals and gradients. version 2 regtype="ll" for local linear, bwmethod="cv.aic" for AIC-based bandwidth selection. It admits control variables.

internal goodCol

Kernel regression version 2 with optional residuals and gradients with regtype="ll" for local linear, bwmethod="cv.aic" for AIC-based bandwidth selection.

Function to compute generalized correlation coefficients r*(x|y) and r*(y|x) from two vectors (not matrices)

internal sales2Lag

internal salesLag

Older version, kernel causality weighted sum allowing control variables

Function reporting detailed kernel causality results in a 7-column matrix (uses deprecated criterion 1, no longer recommended but may be useful for second and third criterion typ=2,3)

Generalized partial correlation coefficients between Xi and Xj, (second version) after removing the effect of Xk, via OLS regression residuals.

Compute generalized (ridge-adjusted) partial correlation coefficients from matrix R*. (deprecated)

Compute the bootstrap probability of correct causal direction.

Report many generalized partial correlation coefficients allowing control variables.

internal nam.badCol

order 4 differencing of a time series vector

Heuristic t test of the difference between two generalized correlations.

order 4 differencing of a matrix of time series

internal nam.mtx0

internal nam.goodCol

Generalized partial correlation coefficient between Xi and Xj after removing the effect of all others. (older version, deprecated)

internal sort.e0

Intermediate weighting function giving Non-Expected Utility theory weights.

Function to compute generalized correlation coefficients r*(x,y).

Create a 3D pillar chart to display (x, y, z) data coordinate surface.

internal sgn.e0

Function reporting kernel causality results as a 7-column matrix, version 2.

Compute probability of positive or negative sign from bootPairs output

Partial correlation coefficient between Xi and Xj after removing the linear effect of all others.

internal rhs.lag2

Compute vectors measuring stochastic dominance of four orders.

internal sort.abse0

Peudo regression coefficients from generalized partial correlation coefficients, (GPCC).

Sort all columns of matrix x with respect to the j-th column.

Residuals of kernel regressions of x on y when both x and y are standardized.

Kernel causality computations admitting control variables reporting a 7-column matrix (has older Cr1)

Block Version of silentPairs for causality scores with control variables

No-print kernel-causality unanimity score matrix with optional control variables

Standardize x and y vectors to achieve zero mean and unit variance.

Kernel causality computations admitting control variables reporting a 7-column matrix, version 2.

Block version reports many generalized partial correlation coefficients allowing control variables.

Vector of hybrid generalized partial correlation coefficients, hybrid version of parcorVec subtracting only linear effects but using generlized correlation between OLS residuals

internal object

Generalized partial correlation coefficients between Xi and Xj, after removing the effect of xk, via nonparametric regression residuals.

Replace asymmetric matrix by max of abs values of [ij] or [ji] elements useful in symmetrizing gmcmtx0 general correlation matrix

No-print kernel causality scores with control variables Hausman-Wu Criterion 1

Function reporting kernel causality results as a 7-column matrix.(deprecated)

Summary magnitudes after removing control variables in several pairs where dependent variable is fixed.

Older kernel-causality unanimity score matrix with optional control variables

Creates input for the stochastic dominance function stochdom2