scholarly journals On Causal Identification under Markov Equivalence

2019 ◽  
Author(s):  
Amin Jaber ◽  
Jiji Zhang ◽  
Elias Bareinboim
Keyword(s):  
Causal Effect ◽  
Causal Structure ◽  
Qualitative Description ◽  
Experimental Distribution ◽  
Independence Model ◽  
Causal Diagrams ◽  
Outcome Set ◽  
Conditional Independence Model ◽  
Markov Equivalence ◽  
Ancestral Graph

In this work, we investigate the problem of computing an experimental distribution from a combination of the observational distribution and a partial qualitative description of the causal structure of the domain under investigation. This description is given by a partial ancestral graph (PAG) that represents a Markov equivalence class of causal diagrams, i.e., diagrams that entail the same conditional independence model over observed variables, and is learnable from the observational data. Accordingly, we develop a complete algorithm to compute the causal effect of an arbitrary set of intervention variables on an arbitrary outcome set.

Predictors of Beliefs about Money

1993 ◽  
Vol 73 (3_suppl) ◽  
pp. 1079-1082 ◽  
Author(s):  
Bruce Kirkcaldy ◽  
Adrian Furnham
Keyword(s):  
Path Analysis ◽  
Achievement Motivation ◽  
Work Ethic ◽  
Causal Effect ◽  
Causal Structure ◽  
Mediating Effect ◽  
Monetary Success

This study was done to examine the causal structure of attitudinal variables that relate to beliefs about money. In all 306 subjects completed various questionnaires measuring the work ethic, achievement motivation, mastery, competitiveness, conformity, and beliefs about money. Path analysis indicated the variables of work ethic, conformity, and mastery operated indirectly through the mediating effect on achievement motivation, competitiveness, and beliefs about money. Factors such as work ethic, mastery, and achievement appear to have a direct causal effect on competitiveness. Ultimately in our culture, monetary success is a result of successful competitiveness.

On partitioning conditional independence model for three-way contingency tables

2011 ◽  
Vol 6 (4) ◽  
pp. 349-355
Author(s):  
Kiyotaka Iki ◽  
Kouji Tahata ◽  
Sadao Tomizawa
Keyword(s):  
Conditional Independence ◽  
Contingency Tables ◽  
Independence Model ◽  
Conditional Independence Model

scholarly journals The Bayesian conditional independence model for measurement error: applications in ecology

2010 ◽  
Vol 18 (2) ◽  
pp. 239-255 ◽  
Author(s):  
Robert J. Denham ◽  
Matthew G. Falk ◽  
Kerrie L. Mengersen
Keyword(s):  
Measurement Error ◽  
Conditional Independence ◽  
Independence Model ◽  
Conditional Independence Model

Characterizing the Minimal Essential Graphs of Maximal Ancestral Graphs

2019 ◽  
Vol 34 (04) ◽  
pp. 2059009
Author(s):  
Yanying Li
Keyword(s):  
Sufficient Conditions ◽  
Compact Representation ◽  
Theory Analysis ◽  
Minimum Number ◽  
Np Hard Problem ◽  
Graph Theory Analysis ◽  
Necessary And Sufficient ◽  
Markov Equivalence ◽  
Ancestral Graph ◽  
Maximal Ancestral Graphs

Learning ancestor graph is a typical NP-hard problem. We consider the problem to represent a Markov equivalence class of ancestral graphs with a compact representation. Firstly, the minimal essential graph is defined to represent the equivalent class of maximal ancestral graphs with the minimum number of invariant arrowheads. Then, an algorithm is proposed to learn the minimal essential graph of ancestral graphs based on the detection of minimal collider paths. It is the first algorithm to use necessary and sufficient conditions for Markov equivalence as a base to seek essential graphs. Finally, a set of orientation rules is presented to orient edge marks of a minimal essential graph. Theory analysis shows our algorithm is sound, and complete in the sense of recognizing all minimal collider paths in a given ancestral graph. And the experiment results show we can discover all invariant marks by these orientation rules.

scholarly journals Integrating Overlapping Datasets Using Bivariate Causal Discovery

2020 ◽  
Vol 34 (04) ◽  
pp. 3781-3790
Author(s):  
Anish Dhir ◽  
Ciaran M. Lee
Keyword(s):  
Conditional Independence ◽  
Causal Structure ◽  
Real Data ◽  
Causal Discovery ◽  
Causal Relations ◽  
Multiple Datasets ◽  
Single Dataset ◽  
Markov Equivalence ◽  
Causal Structures ◽  
Discovery Algorithms

Causal knowledge is vital for effective reasoning in science, as causal relations, unlike correlations, allow one to reason about the outcomes of interventions. Algorithms that can discover causal relations from observational data are based on the assumption that all variables have been jointly measured in a single dataset. In many cases this assumption fails. Previous approaches to overcoming this shortcoming devised algorithms that returned all joint causal structures consistent with the conditional independence information contained in each individual dataset. But, as conditional independence tests only determine causal structure up to Markov equivalence, the number of consistent joint structures returned by these approaches can be quite large. The last decade has seen the development of elegant algorithms for discovering causal relations beyond conditional independence, which can distinguish among Markov equivalent structures. In this work we adapt and extend these so-called bivariate causal discovery algorithms to the problem of learning consistent causal structures from multiple datasets with overlapping variables belonging to the same generating process, providing a sound and complete algorithm that outperforms previous approaches on synthetic and real data.

scholarly journals A Causal Perspective on OSIM2 Data Generation, with Implications for Simulation Study Design and Interpretation

2015 ◽  
Vol 3 (2) ◽  
pp. 177-187 ◽  
Author(s):  
Susan Gruber
Keyword(s):  
Simulation Study ◽  
Real World ◽  
Structural Equation ◽  
Medical Condition ◽  
Causal Effect ◽  
Causal Structure ◽  
Data Generation ◽  
Real World Data ◽  
World Data ◽  
Simulation Scheme

AbstractResearch by the Observational Medical Outcomes Partnership (OMOP) has focused on developing and evaluating strategies to exploit observational electronic data to improve post-market prescription drug surveillance. A data simulator known as OSIM2 developed by the OMOP statistical methods group has been used as a testbed for evaluating and comparing different estimation procedures for detecting adverse drug-related events from data similar to that found in electronic insurance claims data. The simulation scheme produces a longitudinal dataset with millions of observations designed to closely match marginal distributions of important covariates in a known dataset. In this paper we provide a non-parametric structural equation model for the data generating process and construct the associated directed acyclic graph (DAG) depicting the causal structure. These representations reveal key differences between simulated and real-world data, including a departure from longitudinal causal relationships, absence of (presumed) sources of bias and time ordering of covariates that conflicts with reality. The DAG also reveals the presence of unmeasured baseline confounding of the causal effect of a drug on a subsequent medical condition. Conclusions naively drawn from this simulation study could mislead an investigator trying to gain insight into estimator performance on real data. Applying causal inference tools allows us to draw more informed conclusions and suggests modifications to the simulation scheme that would more closely align simulated and real-world data.

Causal Inference, Causal Effect Estimation, and Systematic Error

2019 ◽  
pp. 41-78
Author(s):  
Daniel Westreich
Keyword(s):  
Causal Inference ◽  
Systematic Error ◽  
Causal Effect ◽  
Sufficient Conditions ◽  
Directed Acyclic Graphs ◽  
Confounding Bias ◽  
Acyclic Graphs ◽  
Causal Diagrams ◽  
Alternative Approaches ◽  
Effect Estimation

Chapter 3 discusses basic concepts in causal inference, beginning with an introduction to potential outcomes and definitions of causal contrasts (or causal estimates of effect), concepts, terms, and notation. Many concepts introduced here will be developed further in subsequent chapters. The author discusses sufficient conditions for estimation of causal effects (which are sometimes called causal identification conditions), causal directed acyclic graphs (sometimes called causal diagrams), and four key types of systematic error (confounding bias, missing data bias, selection bias, and measurement error/information bias). The author also briefly discusses alternative approaches to causal inference.

P0811CONFUSION BETWEEN ETIOLOGY AND PREDICTION IN CLINICAL OBSERVATIONAL STUDIES; HOW OFTEN DOES IT ARISE AND HOW CAN WE AVOID IT? A SCOPING REVIEW

2020 ◽  
Vol 35 (Supplement_3) ◽  
Author(s):  
Chava Ramspek ◽  
Friedo W Dekker ◽  
Merel Van Diepen
Keyword(s):  
Kidney Failure ◽  
Observational Studies ◽  
Causal Effect ◽  
Causal Structure ◽  
Medication Use ◽  
Predictive Performance ◽  
Observational Research ◽  
Original Research ◽  
Causal Pathway ◽  
Study Characteristics

Abstract Background and Aims In etiological research the aim is to uncover the causal effect of a specific exposure on an outcome. The aim in prediction research is to predict an outcome with the best accuracy, irrespective of possible causality. Although in observational research both types of studies use similar statistical methods (generally multivariable modelling), the interpretation differs. For example, when researching the causal effect of BMI on kidney failure, it is important to correct for confounders such as age (i.e. factors that causally affect both BMI and kidney failure). Judgement of confounders must be made on pre-existing knowledge. If we select confounders based on the data, we might also correct for hypertension and atherosclerosis (as they are associated with BMI and kidney failure). As this correction is in the causal pathway we would erroneously conclude that BMI does not affect the risk of kidney failure. Vice versa, a mortality prediction model for dialysis patients may include antihypertensive medication use as a predictor. It would be wrong to conclude that patients should discontinue this medication to improve prognosis; the medication use is a marker for a certain health status and we cannot interpret it in a causal manner. Similar to these examples, we’ve found that characteristics from etiology and prediction are often confused, leaving us with studies that may be misinterpreted. The aim of the current study is to quantify the amount of confusion between etiology and prediction in clinical observational studies and identify common mistakes that lead to this confusion. Method Studies published in January 2018 in the top journals of four distinct medical fields: General & Internal medicine, Surgery, Cardiology and Nephrology were screened for inclusion. Original research studies on observational cohorts of humans were included. A list of key study characteristics of etiological and prediction research was developed by CLR and MvD in an iterative fashion. From these characteristics signaling questions for confusion were developed to score included studies. Results The developed key study characteristics of etiology and prediction are shown in the table. In total, 286 studies were screened of which 123 were included. Overall, 27% (n=33) of included articles contained some form of confusion between etiology and prediction. In the figure the journal impact factor is mapped against proportion of confusion per included journal. We can see a trend that as impact factors increase the amount of confusion decreases. In etiological studies, the most frequent (n=15) form of confusion was adjustment for variables based on predictive performance in the data, instead of known causal structure. The majority selected ‘confounders’ purely based on p-values and therefore potentially adjusted for intermediate variables, resulting in incorrect effect estimates. Another mistake in etiological studies (n=5) was the reporting of predictive performance measures such as the C-statistic for an etiological model. In prediction studies the most confusion occurred in the discussion (n=14). Seven studies interpreted predictors causally, for example by concluding that these predictors should be modified in order to improve patient outcomes. As the effect estimates of these studies do not account for confounding, this interpretation is invalid. Lastly, seven studies mention residual confounding as a limitation, which is only a problem in etiological research. Conclusion Confusion between etiology and prediction is a wide-spread methodological flaw in medical observational studies, particularly those published in lower impact clinical journals. As confusion may lead to erroneous conclusions, the distinction between causal and predictive research deserves more attention in medical research and scientific education.

scholarly journals Counting and Sampling from Markov Equivalent DAGs Using Clique Trees

2019 ◽  
Vol 33 ◽  
pp. 3664-3671
Author(s):  
AmirEmad Ghassami ◽  
Saber Salehkaleybar ◽  
Negar Kiyavash ◽  
Kun Zhang
Keyword(s):  
Equivalence Class ◽  
Graphical Model ◽  
Causal Effect ◽  
Ground Truth ◽  
Chordal Graphs ◽  
Underlying Structure ◽  
Bounded Degree ◽  
Additional Information ◽  
Clique Tree ◽  
Markov Equivalence

A directed acyclic graph (DAG) is the most common graphical model for representing causal relationships among a set of variables. When restricted to using only observational data, the structure of the ground truth DAG is identifiable only up to Markov equivalence, based on conditional independence relations among the variables. Therefore, the number of DAGs equivalent to the ground truth DAG is an indicator of the causal complexity of the underlying structure–roughly speaking, it shows how many interventions or how much additional information is further needed to recover the underlying DAG. In this paper, we propose a new technique for counting the number of DAGs in a Markov equivalence class. Our approach is based on the clique tree representation of chordal graphs. We show that in the case of bounded degree graphs, the proposed algorithm is polynomial time. We further demonstrate that this technique can be utilized for uniform sampling from a Markov equivalence class, which provides a stochastic way to enumerate DAGs in the equivalence class and may be needed for finding the best DAG or for causal inference given the equivalence class as input. We also extend our counting and sampling method to the case where prior knowledge about the underlying DAG is available, and present applications of this extension in causal experiment design and estimating the causal effect of joint interventions.

scholarly journals A Graphical Criterion for Effect Identification in Equivalence Classes of Causal Diagrams

2018 ◽  
Author(s):  
Amin Jaber ◽  
Jiji Zhang ◽  
Elias Bareinboim
Keyword(s):  
Observational Data ◽  
Equivalence Class ◽  
State Of The Art ◽  
Causal Structure ◽  
Learning Algorithms ◽  
Equivalence Classes ◽  
Data Driven ◽  
Current State ◽  
Causal Diagrams ◽  
Necessary And Sufficient

Computing the effects of interventions from observational data is an important task encountered in many data-driven sciences. The problem is addressed by identifying the post-interventional distribution with an expression that involves only quantities estimable from the pre-interventional distribution over observed variables, given some knowledge about the causal structure. In this work, we relax the requirement of having a fully specified causal structure and study the identifiability of effects with a singleton intervention (X), supposing that the structure is known only up to an equivalence class of causal diagrams, which is the output of standard structural learning algorithms (e.g., FCI). We derive a necessary and sufficient graphical criterion for the identifiability of the effect of X on all observed variables. We further establish a sufficient graphical criterion to identify the effect of X on a subset of the observed variables, and prove that it is strictly more powerful than the current state-of-the-art result on this problem.

Sign in / Sign up

Export Citation Format

Share Document