A causal perspective on reliability assessment

Abstract Causality in an engineered system pertains to how a system output changes due to a controlled change or intervention on the system or system environment. Engineered systems designs reflect a causal theory regarding how a system will work, and predicting the reliability of such systems typically requires knowledge of this underlying causal structure. The aim of this work is to introduce causal modeling tools that inform reliability predictions based on biased data sources. We present a novel application of the popular structural causal modeling (SCM) framework to reliability estimation in an engineering application, illustrating how this framework can inform whether reliability is estimable and how to estimate reliability given a set of data and assumptions about the subject matter and data generating mechanism. When data are insufficient for estimation, sensitivity studies based on problem-specific knowledge can inform how much reliability estimates can change due to biases in the data and what information should be collected next to provide the most additional information. We apply the approach to a pedagogical example related to a real, but proprietary, engineering application, considering how two types of biases in data can influence a reliability calculation.

[1]  Justin T. Newcomer.  A new approach to quantification of margins and uncertainties for physical simulation data. , 2012 .

[2]  Elias Bareinboim,et al.  External Validity: From Do-Calculus to Transportability Across Populations , 2014, Probabilistic and Causal Inference.

[3]  Kun Jai Lee,et al.  Application of Bayesian network to the probabilistic risk assessment of nuclear waste disposal , 2006, Reliab. Eng. Syst. Saf..

[4]  Jiqiang Guo,et al.  Stan: A Probabilistic Programming Language. , 2017, Journal of statistical software.

[5]  Sankaran Mahadevan,et al.  Validation of reliability computational models using Bayes networks , 2005, Reliab. Eng. Syst. Saf..

[6]  Enrico Zio,et al.  Foundational Issues in Risk Assessment and Risk Management , 2012, Risk analysis : an official publication of the Society for Risk Analysis.

[7]  Sankaran Mahadevan,et al.  Test Resource Allocation in Hierarchical Systems Using Bayesian Networks , 2013 .

[8]  David B. Dunson,et al.  Bayesian Data Analysis , 2010 .

[9]  Sallie Keller-McNulty,et al.  Testing the untestable: reliability in the 21st century , 2003, IEEE Trans. Reliab..

[10]  Onyebuchi A Arah,et al.  Bias Formulas for Sensitivity Analysis of Unmeasured Confounding for General Outcomes, Treatments, and Confounders , 2011, Epidemiology.

[11]  Jon C. Helton,et al.  Ideas underlying the Quantification of Margins and Uncertainties , 2011, Reliab. Eng. Syst. Saf..

[12]  Rumi Ghosh,et al.  Causal Discovery for Manufacturing Domains , 2016, ArXiv.

[13]  Jing Li,et al.  Knowledge discovery from observational data for process control using causal Bayesian networks , 2007 .

[14]  Sankaran Mahadevan,et al.  Selection of model discrepancy priors in Bayesian calibration , 2014, J. Comput. Phys..

[15]  Nima Khakzad,et al.  Safety analysis in process facilities: Comparison of fault tree and Bayesian network approaches , 2011, Reliab. Eng. Syst. Saf..

[16]  Louis Anthony Tony Cox,et al.  Improving Causal Inferences in Risk Analysis , 2013, Risk analysis : an official publication of the Society for Risk Analysis.

[17]  William Q. Meeker,et al.  Reliability: The Other Dimension of Quality , 2004 .

[18]  Galit Shmueli,et al.  To Explain or To Predict? , 2010 .

[19]  Judea Pearl,et al.  Bayesian Networks , 1998, Encyclopedia of Social Network Analysis and Mining. 2nd Ed..

[20]  Timothy C. Wallstrom,et al.  Quantification of margins and uncertainties: A probabilistic framework , 2011, Reliab. Eng. Syst. Saf..

[21]  A. H. Murphy,et al.  Quality/Value Relationship for Imperfect Information in the Umbrella Problem , 1987 .

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

[23]  Sankaran Mahadevan,et al.  Quantification of margins and uncertainties of complex systems in the presence of aleatoric and epistemic uncertainty , 2011, Reliab. Eng. Syst. Saf..

[24]  Benjamin Schroeder,et al.  Distinguishing between model- and data-driven inferences for high reliability statistical predictions , 2018, Reliab. Eng. Syst. Saf..

[25]  David A. Broniatowski,et al.  Assessing causal claims about complex engineered systems with quantitative data: internal, external, and construct validity , 2017, Syst. Eng..

[26]  J. Pearl,et al.  Causal Inference in Statistics: A Primer , 2016 .

[27]  J. Pearl,et al.  Causal inference , 2011, Twenty-one Mental Models That Can Change Policing.

[28]  J. Robins.  Data, Design, and Background Knowledge in Etiologic Inference , 2001, Epidemiology.

[29]  Fumie Yokota,et al.  Value of Information Analysis in Environmental Health Risk Management Decisions: Past, Present, and Future , 2004, Risk analysis : an official publication of the Society for Risk Analysis.

[30]  Luigi Portinale,et al.  Improving the analysis of dependable systems by mapping fault trees into Bayesian networks , 2001, Reliab. Eng. Syst. Saf..

[31]  Elias Bareinboim,et al.  Causal inference and the data-fusion problem , 2016, Proceedings of the National Academy of Sciences.

[32]  Judea Pearl,et al.  Causal Inference , 2010 .

[33]  Louis Anthony Tony Cox.  Clarifying types of uncertainty: when are models accurate, and uncertainties small? , 2011, Risk analysis : an official publication of the Society for Risk Analysis.

[34]  P F Ricci,et al.  Causation in risk assessment and management: models, inference, biases, and a microbial risk-benefit case study. , 2005, Environment international.

[35]  Ronald A. Howard,et al.  Information Value Theory , 1966, IEEE Trans. Syst. Sci. Cybern..