TETRAD - A TOOLBOX FOR CAUSAL DISCOVERY

Climate and Earth research seeks to identify causal relationships without the advantage of experimental controls. Algorithmic methods for that purpose have a long history and have developed rapidly in the last quarter century, so that new methods appear almost monthly. Unsurprisingly, these products vary in accuracy, informativeness, quality of implementation, and necessary assumptions. Researchers need a guide and implementation of well-vetted causal search methods and a means to test and compare methods on real and simulated data. We review the TETRAD suite of programs for these purposes, available from the Pittsburgh/Carnegie Mellon Center for Causal (http://www.phil.cmu.edu/tetrad/).

[1]  E. Barnes,et al.  A study of links between the Arctic and the midlatitude jet stream using Granger and Pearl causality , 2018, Environmetrics.

[2]  Clark Glymour,et al.  A million variables and more: the Fast Greedy Equivalence Search algorithm for learning high-dimensional graphical causal models, with an application to functional magnetic resonance images , 2016, International Journal of Data Science and Analytics.

[3]  Daniel Malinsky,et al.  Comparing the Performance of Graphical Structure Learning Algorithms with TETRAD , 2016, 1607.08110.

[4]  Kazuyuki Aihara,et al.  Detecting Causality by Combined Use of Multiple Methods: Climate and Brain Examples , 2016, PloS one.

[5]  C. O’Brien.  Statistical Learning with Sparsity: The Lasso and Generalizations , 2016 .

[6]  Bernhard Schölkopf,et al.  Discovering Temporal Causal Relations from Subsampled Data , 2015, ICML.

[7]  Bernhard Schölkopf,et al.  Causal Inference by Identification of Vector Autoregressive Processes with Hidden Components , 2015, ICML.

[8]  Jakob Runge,et al.  Quantifying the Strength and Delay of Climatic Interactions: The Ambiguities of Cross Correlation and a Novel Measure Based on Graphical Models , 2014 .

[9]  Imme Ebert-Uphoff,et al.  Weakening of atmospheric information flow in a warming climate in the Community Climate System Model , 2014 .

[10]  Diego Colombo,et al.  Order-independent constraint-based causal structure learning , 2012, J. Mach. Learn. Res..

[11]  M. Eichler.  Causal inference with multiple time series: principles and problems , 2013, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[12]  I. Ebert‐Uphoff,et al.  A new type of climate network based on probabilistic graphical models: Results of boreal winter versus summer , 2012 .

[13]  Imme Ebert-Uphoff,et al.  Causal Discovery for Climate Research Using Graphical Models , 2012 .

[14]  Bernhard Schölkopf,et al.  Kernel-based Conditional Independence Test and Application in Causal Discovery , 2011, UAI.

[15]  Chloe Chen Chen.  Graphical modelling of multivariate time series , 2011 .

[16]  C. Kishtawal,et al.  Observational evidence that agricultural intensification and land use change may be reducing the Indian summer monsoon rainfall , 2010 .

[17]  Aapo Hyvärinen,et al.  On the Identifiability of the Post-Nonlinear Causal Model , 2009, UAI.

[18]  C. Glymour,et al.  Data Driven Methods for Nonlinear Granger Causality: Climate Teleconnection Mechanisms , 2005 .

[19]  R Scheines,et al.  The TETRAD Project: Constraint Based Aids to Causal Model Specification. , 1998, Multivariate behavioral research.

[20]  P. Spirtes,et al.  Causation, prediction, and search , 1993 .

[21]  P. Spirtes,et al.  An Algorithm for Fast Recovery of Sparse Causal Graphs , 1991 .

[22]  C. Granger.  Investigating causal relations by econometric models and cross-spectral methods , 1969 .

[23]  GILBERT WALKER,et al.  World Weather , 1928, Nature.

[24]  G. Yule.  NOTES ON THE THEORY OF ASSOCIATION OF ATTRIBUTES IN STATISTICS , 1903 .