Causality, mediation and time: a dynamic viewpoint

Summary. Time dynamics are often ignored in causal modelling. Clearly, causality must operate in time and we show how this corresponds to a mechanistic, or system, understanding of causality. The established counterfactual definitions of direct and indirect effects depend on an ability to manipulate the mediator which may not hold in practice, and we argue that a mechanistic view may be better. Graphical representations based on local independence graphs and dynamic path analysis are used to facilitate communication as well as providing an overview of the dynamic relations ‘at a glance’. The relationship between causality as understood in a mechanistic and in an interventionist sense is discussed. An example using data from the Swiss HIV Cohort Study is presented.

[1]  James J. Heckman,et al.  1. The Scientific Model of Causality , 2005 .

[2]  A. Dawid Causal Inference without Counterfactuals , 2000 .

[3]  T. Martinussen,et al.  Dynamic path analysis for event time data: large sample properties and inference , 2010, Lifetime data analysis.

[4]  Nancy Cartwright Reply To Steel And Pearl , 2010, Economics and Philosophy.

[5]  Tore Schweder,et al.  Composable Markov processes , 1970, Journal of Applied Probability.

[6]  Andreas Wagner,et al.  Estimating coarse gene network structure from large-scale gene perturbation data. , 2002, Genome research.

[7]  Karol E. Watson Homocysteine lowering and cardiovascular events after acute myocardial infarction , 2007 .

[8]  J. Robins,et al.  Marginal Structural Models and Causal Inference in Epidemiology , 2000, Epidemiology.

[9]  J. Robins A new approach to causal inference in mortality studies with a sustained exposure period—application to control of the healthy worker survivor effect , 1986 .

[10]  Nancy Cartwright Hunting Causes and Using Them: Case studies: Bayes nets and invariance theories , 2007 .

[11]  A. Philip Dawid,et al.  Direct and Indirect Effects of Sequential Treatments , 2006, UAI.

[12]  S. Cole,et al.  Fallibility in estimating direct effects. , 2002, International journal of epidemiology.

[13]  Vanessa Didelez,et al.  Asymmetric Separation for Local Independence Graphs , 2006, UAI.

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

[15]  Per Magne Ueland,et al.  Homocysteine lowering and cardiovascular events after acute myocardial infarction. , 2006, The New England journal of medicine.

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

[17]  P. Monini,et al.  HIV protease inhibitors: antiretroviral agents with anti-inflammatory, anti-angiogenic and anti-tumour activity. , 2003, The Journal of antimicrobial chemotherapy.

[18]  N. Jewell,et al.  Estimation of treatment effects in randomized trials with non‐compliance and a dichotomous outcome , 2004 .

[19]  D P MacKinnon,et al.  The intermediate endpoint effect in logistic and probit regression , 2007, Clinical trials.

[20]  O. Boucher,et al.  A satellite view of aerosols in the climate system , 2002, Nature.

[21]  Mark J van der Laan,et al.  Estimation of Direct Causal Effects , 2006, Epidemiology.

[22]  P. Dennis,et al.  Repositioning HIV protease inhibitors as cancer therapeutics , 2008, Current opinion in HIV and AIDS.

[23]  D. Rubin Direct and Indirect Causal Effects via Potential Outcomes * , 2004 .

[24]  J. Robins,et al.  Estimation of treatment effects in randomised trials with non-compliance and a dichotomous outcome using structural mean models , 2004 .

[25]  S. Maxwell,et al.  Testing mediational models with longitudinal data: questions and tips in the use of structural equation modeling. , 2003, Journal of abnormal psychology.

[26]  Mark Cary,et al.  Causal mediation analyses for randomized trials , 2008, Health Services and Outcomes Research Methodology.

[27]  Sharon Schwartz,et al.  Opening the Black Box: a motivation for the assessment of mediation. , 2009, International journal of epidemiology.

[28]  Demis Basso,et al.  A new method for detecting causality in fMRI data of cognitive processing , 2006, Cognitive Processing.

[29]  D. A. Kenny,et al.  Correlation and Causation , 1937, Wilmott.

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

[31]  Els Goetghebeur,et al.  Estimation of controlled direct effects , 2008 .

[32]  David J. Spiegelhalter,et al.  Local computations with probabilities on graphical structures and their application to expert systems , 1990 .

[33]  O. Aalen,et al.  Survival and Event History Analysis: A Process Point of View , 2008 .

[34]  Michael O'Rourke,et al.  Causation and explanation , 2007 .

[35]  Peter J. Diggle,et al.  Analysis of longitudinal data with drop‐out: objectives, assumptions and a proposal , 2007 .

[36]  D. Freedman Graphical Models for Causation, and the Identification Problem , 2004 .

[37]  Eric Renault,et al.  Option Hedging and Implicit Volatilities. Non Causality in Continuous Time Varma Models , 1993 .

[38]  Richard Emsley,et al.  Ian R White interventions Mediation and moderation of treatment effects in randomised controlled trials of complex , 2010 .

[39]  J. Robins,et al.  Marginal structural models to estimate the causal effect of zidovudine on the survival of HIV-positive men. , 2000, Epidemiology.

[40]  P. Machamer,et al.  Thinking about Mechanisms , 2000, Philosophy of Science.

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

[42]  D. Commenges,et al.  A general dynamical statistical model with causal interpretation , 2009 .

[43]  Xiongzhi Chen Brownian Motion and Stochastic Calculus , 2008 .

[44]  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.

[45]  J. Woodward,et al.  Scientific Explanation and the Causal Structure of the World , 1988 .

[46]  Jaakko Kuorikoski Varieties of Modularity for Causal and Constitutive Explanations , 2008 .

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

[48]  N Keiding,et al.  Event history analysis and inference from observational epidemiology. , 1999, Statistics in medicine.

[49]  Stijn Vansteelandt,et al.  Estimation of direct effects for survival data by using the Aalen additive hazards model , 2011 .

[50]  DIW Coggon,et al.  Time and chance: the stochastic nature of disease causation , 2005, The Lancet.

[51]  Joseph Loscalzo,et al.  Homocysteine trials--clear outcomes for complex reasons. , 2006, The New England journal of medicine.

[52]  Vanessa Didelez Graphical models for composable finite Markov processes , 2007 .

[53]  S. Lauritzen,et al.  Chain graph models and their causal interpretations , 2002 .

[54]  Odd O Aalen,et al.  Dynamic Analysis of Recurrent Event Data Using the Additive Hazard Model , 2006, Biometrical journal. Biometrische Zeitschrift.

[55]  Hansjakob Furrer,et al.  A sequential Cox approach for estimating the causal effect of treatment in the presence of time‐dependent confounding applied to data from the Swiss HIV Cohort Study , 2010, Statistics in medicine.

[56]  Jean-Pierre Florens,et al.  Noncausality in Continuous Time , 1996 .

[57]  Karl J. Friston Causal Modelling and Brain Connectivity in Functional Magnetic Resonance Imaging , 2009, PLoS biology.

[58]  D. Freedman Graphical models for causation, and the identification problem. , 2004, Evaluation review.

[59]  T. VanderWeele Mediation and mechanism , 2009, European Journal of Epidemiology.

[60]  O. Aalen,et al.  Dynamic path analysis—a new approach to analyzing time-dependent covariates , 2006, Lifetime data analysis.

[61]  Tom Burr,et al.  Causation, Prediction, and Search , 2003, Technometrics.

[62]  Olaf Wolkenhauer,et al.  An abstract cell model that describes the self-organization of cell function in living systems. , 2007, Journal of theoretical biology.

[63]  Nancy Cartwright Hunting Causes and Using Them: Plurality in causality , 2007 .

[64]  Eiliv Lund,et al.  Education and risk of breast cancer in the Norwegian‐Swedish women's lifestyle and health cohort study , 2004, International journal of cancer.

[65]  Vanessa Didelez,et al.  Graphical models for marked point processes based on local independence , 2007, 0710.5874.

[66]  C Loehlin John,et al.  Latent variable models: an introduction to factor, path, and structural analysis , 1986 .

[67]  James M. Robins,et al.  Causal inference for complex longitudinal data: the continuous case , 2001 .

[68]  M. Eichler Granger causality and path diagrams for multivariate time series , 2007 .

[69]  Kwang-Hyun Cho,et al.  The dynamic systems approach to control and regulation of intracellular networks , 2005, FEBS letters.

[70]  Kevin G Lynch,et al.  Causal Mediation Analyses with Rank Preserving Models , 2007, Biometrics.

[71]  Peter Spirtes,et al.  Introduction to Causal Inference , 2010, J. Mach. Learn. Res..

[72]  Dylan Small,et al.  Defining and Estimating Intervention Effects for Groups that will Develop an Auxiliary Outcome , 2007 .

[73]  D. A. Kenny,et al.  Correlation and Causation. , 1982 .

[74]  Odd O. Aalen,et al.  A dynamic approach for reconstructing missing longitudinal data using the linear increments model , 2010, Biostatistics.

[75]  Arnoldo Frigessi,et al.  What can Statistics Contribute to a Causal Understanding? , 2007 .

[76]  Michael Eichler,et al.  On Granger causality and the effect of interventions in time series , 2009, Lifetime data analysis.

[77]  M. Hernán A definition of causal effect for epidemiological research , 2004, Journal of Epidemiology and Community Health.

[78]  D. Rubin Estimating causal effects of treatments in randomized and nonrandomized studies. , 1974 .

[79]  Jonathan AC Sterne,et al.  Long-term effectiveness of potent antiretroviral therapy in preventing AIDS and death: a prospective cohort study , 2005, The Lancet.

[80]  Eric Renault,et al.  Noncausality in Continuous Time Models , 1996, Econometric Theory.

[81]  Odd O. Aalen,et al.  Dynamic modelling and causality , 1987 .

[82]  A. Telenti,et al.  Clinical progression and virological failure on highly active antiretroviral therapy in HIV-1 patients: a prospective cohort study , 1999, The Lancet.

[83]  S. Shen-Orr,et al.  Network motifs in the transcriptional regulation network of Escherichia coli , 2002, Nature Genetics.

[84]  S. Wright The Method of Path Coefficients , 1934 .

[85]  J M Andrieu,et al.  HIV protease inhibitors restore impaired T-cell proliferative response in vivo and in vitro: a viral-suppression-independent mechanism. , 2000, Blood.

[86]  Theis Lange,et al.  Direct and Indirect Effects in a Survival Context , 2011, Epidemiology.

[87]  Varun Grover,et al.  The Use of Structural Equation Modeling in IS Research: Review and Recommendations , 2004 .

[88]  J. Heckman,et al.  Econometric Causality , 2008 .

[89]  K. Røysland A martingale approach to continuous-time marginal structural models , 2009, 0901.2593.

[90]  J. Robins,et al.  Identifiability and Exchangeability for Direct and Indirect Effects , 1992, Epidemiology.

[91]  J. Robins Correcting for non-compliance in randomized trials using structural nested mean models , 1994 .

[92]  R. Francis,et al.  Back pain in osteoporotic vertebral fractures , 2008, Osteoporosis International.

[93]  Elja Arjas,et al.  Causal Inference from Observational Data: A Bayesian Predictive Approach , 2012 .

[94]  James B. Elsner,et al.  Granger causality and Atlantic hurricanes , 2007 .

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

[96]  Tipu Z. Aziz,et al.  Revealing the dynamic causal interdependence between neural and muscular signals in Parkinsonian tremor , 2007, J. Frankl. Inst..

[97]  D. R. Cox,et al.  Causal Inference Without Counterfactuals: Comment , 2000 .

[98]  M. A. Girshick,et al.  Statistical Analysis of the Demand for Food: Examples of Simultaneous Estimation of Structural Equations , 1947 .

[99]  J. Robins,et al.  Instruments for Causal Inference: An Epidemiologist's Dream? , 2006, Epidemiology.