tag:crantastic.org,2005:/packages/generalCorrLatest activity for generalCorr2019-10-30T21:01:36Zcrantastic.orgtag:crantastic.org,2005:TimelineEvent/942542019-10-30T21:01:36Z2019-10-30T21:01:36ZgeneralCorr was upgraded to version 1.1.5<a href="/packages/generalCorr">generalCorr</a> was <span class="action">upgraded</span> to version <a href="/packages/generalCorr/versions/89606">1.1.5</a><br /><h3>Package description:</h3><p>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 value 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 parcorBMany() reports generalized partials between the first variable and all others. The package provides additional R tools for causal assessment, "outlier detection," and for numerical integration by the trapezoidal rule, stochastic dominance, pillar 3D charts, etc. We also provide functions for bootstrap-based statistical inference for causal paths. causeSummary() and causeSummBlk() are easiest to use functions.</p>crantastic.orgtag:crantastic.org,2005:TimelineEvent/934702019-10-07T17:21:30Z2019-10-07T17:21:30ZgeneralCorr was upgraded to version 1.1.3<a href="/packages/generalCorr">generalCorr</a> was <span class="action">upgraded</span> to version <a href="/packages/generalCorr/versions/88855">1.1.3</a><br /><h3>Package description:</h3><p>Since causal paths from data are important for all sciences, the package provides many sophisticated functions. causeSummary() 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 value 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 parcorMany() reports generalized partials between the first variable and all others. The package provides additional R tools for causal assessment, "outlier detection," and for numerical integration by the trapezoidal rule, stochastic dominance, pillar 3D charts, etc. We also provide functions for bootstrap-based statistical inference for causal paths.</p>crantastic.orgtag:crantastic.org,2005:TimelineEvent/774162018-07-12T07:41:12Z2018-07-12T07:41:12ZgeneralCorr was upgraded to version 1.1.2<a href="/packages/generalCorr">generalCorr</a> was <span class="action">upgraded</span> to version <a href="/packages/generalCorr/versions/73891">1.1.2</a><br /><h3>Package description:</h3><p>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.</p>crantastic.orgtag:crantastic.org,2005:TimelineEvent/708052018-01-24T19:21:10Z2018-01-24T19:21:10ZgeneralCorr was upgraded to version 1.1.1<a href="/packages/generalCorr">generalCorr</a> was <span class="action">upgraded</span> to version <a href="/packages/generalCorr/versions/67632">1.1.1</a><br /><h3>Package description:</h3><p>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. 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)|> |r*(y|x)| 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 and one for a heuristic t-test.</p>crantastic.orgtag:crantastic.org,2005:TimelineEvent/700102018-01-05T05:20:58Z2018-01-05T05:20:58ZgeneralCorr was upgraded to version 1.1.0<a href="/packages/generalCorr">generalCorr</a> was <span class="action">upgraded</span> to version <a href="/packages/generalCorr/versions/66890">1.1.0</a><br /><h3>Package description:</h3><p>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. 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)|> |r*(y|x)| 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 and one for a heuristic t-test.</p>crantastic.orgtag:crantastic.org,2005:TimelineEvent/670142017-10-03T23:01:03Z2017-10-03T23:01:03ZgeneralCorr was upgraded to version 1.0.9<a href="/packages/generalCorr">generalCorr</a> was <span class="action">upgraded</span> to version <a href="/packages/generalCorr/versions/64100">1.0.9</a><br /><h3>Package description:</h3><p>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. 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 gradients (Cr1) and absolute residuals (Cr2), 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)|> |r*(y|x)| it suggests that y is more likely the "kernel cause" of x. The usual partial correlations are generalized for the asymmetric matrix of r*'s 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 and one for a heuristic t-test.</p>crantastic.orgtag:crantastic.org,2005:TimelineEvent/663182017-09-11T14:40:55Z2017-09-11T14:40:55ZgeneralCorr was upgraded to version 1.0.8<a href="/packages/generalCorr">generalCorr</a> was <span class="action">upgraded</span> to version <a href="/packages/generalCorr/versions/63438">1.0.8</a><br /><h3>Package description:</h3><p>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. 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 gradients (Cr1) and absolute residuals (Cr2), 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)|> |r*(y|x)| it suggests that y is more likely the "kernel cause" of x. The usual partial correlations are generalized for the asymmetric matrix of r*'s 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 and one for a heuristic t-test.</p>crantastic.orgtag:crantastic.org,2005:TimelineEvent/660632017-09-02T16:01:04Z2017-09-02T16:01:04ZgeneralCorr was upgraded to version 1.0.7<a href="/packages/generalCorr">generalCorr</a> was <span class="action">upgraded</span> to version <a href="/packages/generalCorr/versions/63183">1.0.7</a><br /><h3>Package description:</h3><p>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. 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 gradients (Cr1) and absolute residuals (Cr2), 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)|> |r*(y|x)| it suggests that y is more likely the "kernel cause" of x. The usual partial correlations are generalized for the asymmetric matrix of r*'s 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 and one for a heuristic t-test.</p>crantastic.orgtag:crantastic.org,2005:TimelineEvent/647832017-07-22T13:00:55Z2017-07-22T13:00:55ZgeneralCorr was upgraded to version 1.0.6<a href="/packages/generalCorr">generalCorr</a> was <span class="action">upgraded</span> to version <a href="/packages/generalCorr/versions/61960">1.0.6</a><br /><h3>Package description:</h3><p>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. 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 gradients (Cr1) and absolute residuals (Cr2), 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)|> |r*(y|x)| it suggests that y is more likely the "kernel cause" of x. The usual partial correlations are generalized for the asymmetric matrix of r*'s 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 and one for a heuristic t-test.</p>crantastic.orgtag:crantastic.org,2005:TimelineEvent/635832017-06-16T18:21:16Z2017-06-16T18:21:16ZgeneralCorr was upgraded to version 1.0.5<a href="/packages/generalCorr">generalCorr</a> was <span class="action">upgraded</span> to version <a href="/packages/generalCorr/versions/60815">1.0.5</a><br /><h3>Package description:</h3><p>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. 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 gradients (Cr1) and absolute residuals (Cr2), 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)|> |r*(y|x)| it suggests that y is more likely the "kernel cause" of x. The usual partial correlations are generalized for the asymmetric matrix of r*'s 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 and one for a heuristic t-test.</p>crantastic.orgtag:crantastic.org,2005:TimelineEvent/633242017-06-08T04:40:52Z2017-06-08T04:40:52ZgeneralCorr was upgraded to version 1.0.4<a href="/packages/generalCorr">generalCorr</a> was <span class="action">upgraded</span> to version <a href="/packages/generalCorr/versions/60556">1.0.4</a><br /><h3>Package description:</h3><p>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. 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 gradients (Cr1) and absolute residuals (Cr2), 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)|> |r*(y|x)| it suggests that y is more likely the "kernel cause" of x. The usual partial correlations are generalized for the asymmetric matrix of r*'s 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 and one for a heuristic t-test.</p>crantastic.orgtag:crantastic.org,2005:TimelineEvent/524592016-06-28T18:20:35Z2016-06-28T18:20:35ZgeneralCorr was upgraded to version 1.0.3<a href="/packages/generalCorr">generalCorr</a> was <span class="action">upgraded</span> to version <a href="/packages/generalCorr/versions/50627">1.0.3</a><br /><h3>Package description:</h3><p>Asymmetric generalized correlations r*(x|y) measure strength of the dependence of x on y. If |r*(x|y)|> |r*(y|x)| it suggests that y is more likely the "kernel cause" of x. There are at least two additional ways of comparing two kernel regressions helping identify the `cause'. In simultaneous equation models where endogeneity of regressors is feared, we can use Prof. Koopmans' method to ignore endogeneity problems when it kernel causes the dependent variable. The usual partial correlations can be generalized for the asymmetric matrix of r*'s. 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 detections 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 and one for a heuristic t-test.</p>crantastic.orgtag:crantastic.org,2005:TimelineEvent/517652016-06-04T17:40:40Z2016-06-04T17:40:40ZgeneralCorr was upgraded to version 1.0.2<a href="/packages/generalCorr">generalCorr</a> was <span class="action">upgraded</span> to version <a href="/packages/generalCorr/versions/49996">1.0.2</a><br /><h3>Package description:</h3><p>Asymmetric generalized correlations r*(x|y) measure strength of the dependence of x on y. If |r*(x|y)|> |r*(y|x)| it suggests that y is more likely the "kernel cause" of x. There are at least two additional ways of comparing two kernel regressions helping identify the `cause'. In simultaneous equation models where endogeneity of regressors is feared, we can use Prof. Koopmans' method to ignore endogeneity problems when it kernel causes the dependent variable. The usual partial correlations can be generalized for the asymmetric matrix of r*'s. 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 detections 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 a function for bootstrap-based statistical inference and one for a heuristic t-test.</p>crantastic.orgtag:crantastic.org,2005:TimelineEvent/514082016-05-20T22:20:56Z2016-05-20T22:20:56ZgeneralCorr was upgraded to version 1.0.1<a href="/packages/generalCorr">generalCorr</a> was <span class="action">upgraded</span> to version <a href="/packages/generalCorr/versions/49655">1.0.1</a><br /><h3>Package description:</h3><p>Asymmetric generalized correlations r*(x|y) measure strength of the dependence of x on y. If |r*(x|y)|> |r*(y|x)| it suggests that y is more likely the "kernel cause" of x. There are at least two additional ways of comparing two kernel regressions helping identify the `cause'. In simultaneous equation models where endogeneity of regressors is feared, we can use Prof. Koopmans' method to ignore endogeneity problems when it kernel causes the dependent variable. The usual partial correlations can be generalized for the asymmetric matrix of r*'s. 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 detections 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 a function for bootstrap-based statistical inference and one for a heuristic t-test.</p>crantastic.orgtag:crantastic.org,2005:TimelineEvent/508312016-05-02T04:40:40Z2016-05-02T04:40:40ZgeneralCorr was released<a href="/packages/generalCorr">generalCorr</a> was <span class="action">released</span><br /><h3>Package description:</h3><p>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 value 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 parcorBMany() reports generalized partials between the first variable and all others. The package provides additional R tools for causal assessment, "outlier detection," and for numerical integration by the trapezoidal rule, stochastic dominance, pillar 3D charts, etc. We also provide functions for bootstrap-based statistical inference for causal paths. causeSummary() and causeSummBlk() are easiest to use functions.</p>crantastic.org