The issue of control in multivariate systems. A contribution of structural modelling

This paper builds upon Judea Pearl’s directed acyclic graphs approach to causality and the tradition of structural modelling in economics and social science. The paper re- examines the issue of control in complex systems with multiple causes and outcomes, in a specific perspective of structural modelling. It begins with three-variable saturated and unsaturated models, and then examines more complex systems including models with collider and latent confounder discussed by Pearl. In particular, focusing on the causes of an outcome, the paper proposes two simple rules for selecting the variables to be controlled for when studying the direct effect of a cause on an outcome of interest or the total effect when dealing with multiple causal paths. This paper presents a model building strategy that allows a statistical model to be considered as structural. The challenge for the model builder amounts to developing an explanation through a recursive decomposition of the joint distribution of the variables congruent with background knowledge and stable with respect to specified changes of the environment.

[1]  P. Holland.  Statistics and Causal Inference , 1985 .

[2]  Luc BAUWENS,et al.  Handbook of Volatility Models and Their Applications , 2012 .

[3]  Judea Pearl,et al.  Linear Models: A Useful “Microscope” for Causal Analysis , 2013 .

[4]  Philippe De Donder,et al.  The political choice of social long term care transfers when family gives time and money , 2015, Soc. Choice Welf..

[5]  Michel Mouchart,et al.  Structural Modelling, Exogeneity, and Causality , 2009 .

[6]  J. Hindriks,et al.  Equilibrium leadership in tax competition models with capital ownership: a rejoinder , 2017 .

[7]  Eliseo Díaz González,et al.  Intermediate Public Economics , 2007 .

[8]  Chava Nachmias,et al.  Research Methods in the Social Sciences , 1976 .

[9]  Michel Mouchart,et al.  Functions and Mechanisms in Structural-Modelling Explanations , 2014 .

[10]  Barbara J. Bird,et al.  Control variables: use, misuse and recommended use , 2014 .

[11]  R. Amir.  Supermodularity and Complementarity in Economics: An Elementary Survey , 2003 .

[12]  Paul Windrum,et al.  A Critical Guide to Empirical Validation of Agent-Based Models in Economics: Methodologies, Procedures, and Open Problems , 2007 .

[13]  Pierre Dehez,et al.  Multiple Causation, Apportionment, and the Shapley Value , 2015, The Journal of Legal Studies.

[14]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[15]  J. Pearl.  The Mediation Formula: A Guide to the Assessment of Causal Pathways in Nonlinear Models , 2011 .

[16]  Phyllis Illari,et al.  Causality: Philosophical Theory meets Scientific Practice , 2014 .

[17]  Sure outcomes of random events: a model for clinical trials , 2001, Statistics in medicine.

[18]  Marcia J. Simmering,et al.  Control Variable Use and Reporting in Macro and Micro Management Research , 2012 .

[19]  J. Pearl.  Causality: Models, Reasoning and Inference , 2000 .

[20]  Sander Greenland,et al.  Modern Epidemiology 3rd edition , 1986 .

[21]  François Maniquet,et al.  Equality Of Opportunity: The Economics Of Responsibility , 2012 .

[22]  Jean Hindriks,et al.  Quel avenir pour nos pensions ? Les grands défis de la réforme des pensions , 2015 .

[23]  A. Ruszczynski.  Stochastic Programming Models , 2003 .

[24]  J. Heckman,et al.  Causality and Econometrics , 2022, SSRN Electronic Journal.

[25]  Nigar Hashimzade,et al.  Solutions Manual to Accompany Intermediate Public Economics 2nd edition , 2013 .

[26]  A. Zellner.  Causality and econometrics , 1979 .

[27]  J. E. Kerrich.  STATISTICAL INFERENCE IN DYNAMIC ECONOMIC MODELS , 1951 .

[28]  G. Wunsch.  Confounding and control , 2007 .

[29]  D. A. Kenny,et al.  The moderator-mediator variable distinction in social psychological research: conceptual, strategic, and statistical considerations. , 1986, Journal of personality and social psychology.

[30]  Paul E. Spector,et al.  Methodological Urban Legends: The Misuse of Statistical Control Variables , 2011 .

[31]  Judea Pearl,et al.  Comment: Graphical Models, Causality and Intervention , 2016 .

[32]  Jacques-François Thisse,et al.  Economic Geography and the Unequal Development of Regions , 2012 .

[33]  Michel Mouchart,et al.  Causal explanation: Recursive decompositions and mechanisms , 2011 .

[34]  Russel A. Jones.  Méthodes de recherche en sciences humaines , 1999 .

[35]  Judea Pearl,et al.  Direct and Indirect Effects , 2001, UAI.

[36]  E. Schokkaert,et al.  Empirical Social Choice , 2011 .

[37]  D. Cox.  Causality : some statistical aspects , 1992 .

[38]  Tjalling C. Koopmans,et al.  Measurement Without Theory , 1947 .

[39]  Jon Williamson,et al.  What is a mechanism? Thinking about mechanisms across the sciences , 2012 .

[40]  M. Hernán,et al.  Causal knowledge as a prerequisite for confounding evaluation: an application to birth defects epidemiology. , 2002, American journal of epidemiology.

[41]  Judea Pearl,et al.  Bayesian decision methods , 1990 .

[42]  David V. Pritchett.  Econometric policy evaluation: A critique , 1976 .

[43]  W. Lam.  Switching Costs in Two‐Sided Markets , 2017 .

[44]  Earl R. Babbie,et al.  The practice of social research , 1969 .

[45]  Federica Russo.  What Invariance Is and How to Test for It , 2014 .

[46]  G. Myles,et al.  Intermediate Public Economics 2nd edition , 2013 .

[47]  Thomas E. Becker.  Potential Problems in the Statistical Control of Variables in Organizational Research: A Qualitative Analysis With Recommendations , 2005 .

[48]  Michel Mouchart,et al.  Inferring causal relations by modelling structures , 2010 .