Graphical Models for Inference with Missing Data

By Max Welling, Zoubin Ghahramani, Kilian Q. Weinberger. 2013

210 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Semi-supervised learning, causality, and the conditional cluster assumption (2019, background): “ely. This may appear at 13Interestingly, such conditioning may allow to extend SSL to settings where the missingness mechanism depends on X C, i.e., covariate-shifted or missing-at-random (MAR) data (Mohan et al., 2013; Sugiyama and Kawanabe, 2012). odds with the result that SSL in the causal direct”
Thinking Clearly About Correlations and Causation: Graphical Causal Models for Observational Data (2017, methodology): “Thoemmes and Mohan (2015) used DAGs based on formalizations by Mohan, Pearl, and Tian (2013) to provide visual representations of missing- data scenarios.”
The seven tools of causal inference, with reflections on machine learning (2019, methodology): “Using causal models of the missingness process we can now formalize the conditions under which causal and probabilistic relationships can be recovered from incomplete data and, whenever the conditions are satisfied, produce a consistent estimate of the desired relationship [Mohan and Pearl 2018; Moh”
Opportunities in Machine Learning for Healthcare (2018, unknown): “ften impractical due to cost and volume. Learning from incomplete,or missing, data has receivedrelativelylittle attentionin the machinelearningcommunity (exceptions include, e.g., Marlin et al. 2011; Mohan et al. 2013; McDermott et al. 2018), but is an actively studied topic in statistics (e.g., Din”
Missing Data as a Causal and Probabilistic Problem (2015, methodology): “When neither MCAR nor MAR holds, data is said to be Missing Not At Random (MNAR), and in this case a characterization of recoverability is an open problem, although many sufficient conditions for recoverability are known [7, 6].”
Missing data and multiple imputation in clinical epidemiological research (2017, unknown): “Graph theories have been helpful in a number of disciplines in the fields of mathematics, engineering, computer science, and biology to determine or evaluate the mechanisms of missingness.(9) In epidemiological research, causal graphical models, such as directed acyclic graphs (DAGs), can be used to”
Causality matters in medical imaging (2019, background): “Causal diagrams again prove instrumental in identifying such structural assumptions about miss-ingness mechanisms 36,37 .”
Graphical Representation of Missing Data Problems (2015, methodology): “We present a graphical representation of missing data mechanism, formalized in Mohan, Pearl, and Tian (2013).”