About

Ema Perkovic is the Dorothy Gilford Early Career Endowed Professor in Mathematical Statistics at the Department of Statistics at the University of Washington. Her research focuses on causal inference through the lens of probabilistic graphical models. She is interested in using graphical models to develop intuitive methodologies for causal identification and estimation from observational data and expert knowledge. Ema Perkovic completed her Ph.D. under the supervision of Marloes Maathuis at the Seminar for Statistics (SfS), ETH Zurich.

Research topics

• Computer Science
• Algorithm
• Statistics
• Mathematics
• Artificial Intelligence
• Combinatorics
• Genetics
• Discrete mathematics
• Applied mathematics
• Biology

Selected publications

• Identifying Conditional Causal Effects in MPDAGs

  ArXiv.org · 2025-07-21

  articleOpen accessSenior author

  We consider identifying a conditional causal effect when a graph is known up to a maximally oriented partially directed acyclic graph (MPDAG). An MPDAG represents an equivalence class of graphs that is restricted by background knowledge and where all variables in the causal model are observed. We provide three results that address identification in this setting: an identification formula when the conditioning set is unaffected by treatment, a generalization of the well-known do calculus to the MPDAG setting, and an algorithm that is complete for identifying these conditional effects.

  PublisherOA PDF

• Conditional Adjustment in a Markov Equivalence Class

  arXiv (Cornell University) · 2023-11-11

  preprintOpen accessSenior author

  We consider the problem of identifying a conditional causal effect through covariate adjustment. We focus on the setting where the causal graph is known up to one of two types of graphs: a maximally oriented partially directed acyclic graph (MPDAG) or a partial ancestral graph (PAG). Both MPDAGs and PAGs represent equivalence classes of possible underlying causal models. After defining adjustment sets in this setting, we provide a necessary and sufficient graphical criterion -- the conditional adjustment criterion -- for finding these sets under conditioning on variables unaffected by treatment. We further provide explicit sets from the graph that satisfy the conditional adjustment criterion, and therefore, can be used as adjustment sets for conditional causal effect identification.

  PublisherOA PDFDOI

• Variable elimination, graph reduction and efficient g-formula

  arXiv (Cornell University) · 2022-02-24

  preprintOpen access

  We study efficient estimation of an interventional mean associated with a point exposure treatment under a causal graphical model represented by a directed acyclic graph without hidden variables. Under such a model, it may happen that a subset of the variables are uninformative in that failure to measure them neither precludes identification of the interventional mean nor changes the semiparametric variance bound for regular estimators of it. We develop a set of graphical criteria that are sound and complete for eliminating all the uninformative variables so that the cost of measuring them can be saved without sacrificing estimation efficiency, which could be useful when designing a planned observational or randomized study. Further, we construct a reduced directed acyclic graph on the set of informative variables only. We show that the interventional mean is identified from the marginal law by the g-formula (Robins, 1986) associated with the reduced graph, and the semiparametric variance bounds for estimating the interventional mean under the original and the reduced graphical model agree. This g-formula is an irreducible, efficient identifying formula in the sense that the nonparametric estimator of the formula, under regularity conditions, is asymptotically efficient under the original causal graphical model, and no formula with such property exists that only depends on a strict subset of the variables.

  PublisherOA PDFDOI

• Graphical Criteria for Efficient Total Effect Estimation Via Adjustment in Causal Linear Models

  Journal of the Royal Statistical Society Series B (Statistical Methodology) · 2022 · 60 citations

  • Computer Science
  • Mathematics
  • Computer Science

  Abstract Covariate adjustment is a commonly used method for total causal effect estimation. In recent years, graphical criteria have been developed to identify all valid adjustment sets, that is, all covariate sets that can be used for this purpose. Different valid adjustment sets typically provide total causal effect estimates of varying accuracies. Restricting ourselves to causal linear models, we introduce a graphical criterion to compare the asymptotic variances provided by certain valid adjustment sets. We employ this result to develop two further graphical tools. First, we introduce a simple variance decreasing pruning procedure for any given valid adjustment set. Second, we give a graphical characterization of a valid adjustment set that provides the optimal asymptotic variance among all valid adjustment sets. Our results depend only on the graphical structure and not on the specific error variances or edge coefficients of the underlying causal linear model. They can be applied to directed acyclic graphs (DAGs), completed partially directed acyclic graphs (CPDAGs) and maximally oriented partially directed acyclic graphs (maximal PDAGs). We present simulations and a real data example to support our results and show their practical applicability.

  PublisherDOI

• The Phantom Pattern Problem: The Mirage of Big Data,

  The American Statistician · 2022-01-02 · 1 citations

  articleOpen access1st authorCorresponding
  PublisherOA PDFDOI

• Variable elimination, graph reduction and the efficient g-formula

  Biometrika · 2022-11-17 · 1 citations

  articleOpen accessCorresponding

  Summary We study efficient estimation of an interventional mean associated with a point exposure treatment under a causal graphical model represented by a directed acyclic graph without hidden variables. Under such a model, a subset of the variables may be uninformative, in that failure to measure them neither precludes identification of the interventional mean nor changes the semiparametric variance bound for regular estimators of it. We develop a set of graphical criteria that are sound and complete for eliminating all the uninformative variables, so that the cost of measuring them can be saved without sacrificing estimation efficiency, which could be useful when designing a planned observational or randomized study. Further, we construct a reduced directed acyclic graph on the set of informative variables only. We show that the interventional mean is identified from the marginal law by the g-formula (Robins, 1986) associated with the reduced graph, and the semiparametric variance bounds for estimating the interventional mean under the original and the reduced graphical model agree. The g-formula is an irreducible, efficient identifying formula in the sense that the nonparametric estimator of the formula, under regularity conditions, is asymptotically efficient under the original causal graphical model, and no formula with this property exists that depends only on a strict subset of the variables.

  PublisherOA PDFDOI

• Leadership in Statistics and Data Science: Planning for Inclusive Excellence,

  The American Statistician · 2022-07-03

  article1st authorCorresponding
  PublisherDOI

• Minimal enumeration of all possible total effects in a Markov equivalence class

  International Conference on Artificial Intelligence and Statistics · 2021-03-18 · 2 citations

  articleSenior author

  In observational studies, when a total causal effect of interest is not identified, the set of all possible effects can be reported instead. This typically occurs when the underlying causal DAG is only known up to a Markov equivalence class, or a refinement thereof due to background knowledge. As such, the class of possible causal DAGs is represented by a maximally oriented partially directed acyclic graph (MPDAG), which contains both directed and undirected edges. We characterize the minimal additional edge orientations required to identify a given total effect. A recursive algorithm is then developed to enumerate subclasses of DAGs, such that the total effect in each subclass is identified as a distinct functional of the observed distribution. This resolves an issue with existing methods, which often report possible total effects with duplicates, namely those that are numerically distinct due to sampling variability but are in fact causally identical.

  Publisher

• Minimal enumeration of all possible total effects in a Markov\n equivalence class

  arXiv (Cornell University) · 2020 · 2 citations

  Senior authorCorresponding
  • Computer Science
  • Mathematics
  • Artificial Intelligence

  In observational studies, when a total causal effect of interest is not\nidentified, the set of all possible effects can be reported instead. This\ntypically occurs when the underlying causal DAG is only known up to a Markov\nequivalence class, or a refinement thereof due to background knowledge. As\nsuch, the class of possible causal DAGs is represented by a maximally oriented\npartially directed acyclic graph (MPDAG), which contains both directed and\nundirected edges. We characterize the minimal additional edge orientations\nrequired to identify a given total effect. A recursive algorithm is then\ndeveloped to enumerate subclasses of DAGs, such that the total effect in each\nsubclass is identified as a distinct functional of the observed distribution.\nThis resolves an issue with existing methods, which often report possible total\neffects with duplicates, namely those that are numerically distinct due to\nsampling variability but are in fact causally identical.\n

  PublisherOA PDFDOI

• Minimal enumeration of all possible total effects in a Markov equivalence class

  arXiv (Cornell University) · 2020-10-16

  preprintOpen accessSenior author

  In observational studies, when a total causal effect of interest is not identified, the set of all possible effects can be reported instead. This typically occurs when the underlying causal DAG is only known up to a Markov equivalence class, or a refinement thereof due to background knowledge. As such, the class of possible causal DAGs is represented by a maximally oriented partially directed acyclic graph (MPDAG), which contains both directed and undirected edges. We characterize the minimal additional edge orientations required to identify a given total effect. A recursive algorithm is then developed to enumerate subclasses of DAGs, such that the total effect in each subclass is identified as a distinct functional of the observed distribution. This resolves an issue with existing methods, which often report possible total effects with duplicates, namely those that are numerically distinct due to sampling variability but are in fact causally identical.

  PublisherOA PDFDOI

Frequent coauthors

• Marloes H. Maathuis

  6 shared

• Markus Kalisch

  ETH Zurich

  6 shared

• Johannes Textor

  4 shared

• F Richard Guo

  University of Michigan–Ann Arbor

  3 shared

• F. Richard Guo

  3 shared

• Andrea Rotnitzky

  2 shared

• Sara LaPlante

  1 shared

• Maloes H. Maathuis

  1 shared

Education

• PhD in Statistics, Mathematics, Seminar for Statistics

  ETH Zurich

  2018

• MSc in Statistics, Mathematics, Seminar for Statistics

  ETH Zurich

  2014

• BSc in Mathematics (Statistics), Mathematics

  University of Belgrade

  2012