Semiparametric Theory and Missing Data

By Anastasios A. Tsiatis. 2006

1,522 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistics and Probability

How researchers see this paper

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

In Artificial Intelligence

In Statistics and Probability

Citations in the corpus

Missing Data Imputation for Supervised Learning (2016, neutral): “Researchers typically assume data is MAR, which mitigates the identiﬁability problems of MNAR because the probability of missing-ness depends on data that are observed on all individuals (Tsiatis, 2007, Chap.”
Efficiently Breaking the Curse of Horizon in Off-Policy Evaluation with Double Reinforcement Learning (2019, methodology): “This type of estimator would be locally efficient estimator in the sense that it is efficient when the model for fw(s) is well-specified (Tsiatis, 2006).”
Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement Learning (2019, background): “If the Q-function is well specified, DR is locally efficient in the sense that its asymptotic MSE achieves the semiparametric lower bound [33].”
Demystifying Double Robustness: A Comparison of Alternative Strategies for Estimating a Population Mean from Incomplete Data (2007, background): “After we drafted our article, a number of important works on DR estimators appeared, including Tan’s (2006) article on causal inference, the monograph by Tsiatis (2006) and the recent articles and technical reports cited by Robins, Sued, Lei-Gomez and Rotnitzky.”
Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes (2019, background): “For a more general and complete presentation, we refer the reader to Bickel et al. (1998); Kosorok (2008); Tsiatis (2006); van der Vaart (1998).”
Quasi-oracle estimation of heterogeneous treatment effects (2017, methodology): “In doing so, we build on the research program developed in van der Laan and Dudoit (2003), van der Laan and Rubin (2006) and van der Laan, Polley, and Hubbard (2007), and later fleshed out for the context of individualized treatment rules by Luedtke and van der Laan (2016a,b,c).”
Estimation of Conditional Average Treatment Effects With High-Dimensional Data (2019, background): “…and Rotnitzky (1995), Hahn (1998), van der Laan and Robins (2003), Hirano, Imbens, and Ridder (2003), van der Laan and Rubin (2006), Firpo (2007), Tsiatis (2007), van der Laan and Rose (2011), Belloni et al. (2017), Farrell (2015), Kennedy et al. (2017), Robins et al. (2017), Wager and Athey…”
Long-term Causal Inference Under Persistent Confounding via Data Combination (2022, background): “Equation (6) means that the conditional distributions of (U,X) | A on the experimental and observational data have enough overlap, which is also a common assumption in missing data literature [Tsiatis, 2007].”
Robust Inference on Average Treatment Effects with Possibly More Covariates than Observations (2013, positive): “This theorem generalizes Lounici, Pontil, van de Geer, and Tsybakov (2011) to the nonparametric, approximately sparse case, improves the sparsity bound, and gives out of sample prediction (imputation) results.”
Semiparametric theory and empirical processes in causal inference (2015, methodology): “To characterize full-data influence functions in causal inf erence problems we need to start by presenting causal inference as a missing dat a problem [54, 53].”
Efficiency Bounds for Missing Data Models with Semiparametric Restrictions (2008, background): “Robins, Rotnitzky and Zhao (1994, Proposition 2.3, p. 850) derived the e¢ cient in uence function for this problem and proposed a locally e¢ cient augmented inverse probability weighting (AIPW) estimator (cf., Scharfstein, Rotnitzky and Robins, 1999; Bang and Robins, 2005; Tsiatis, 2006).”
Dynamic Regime Marginal Structural Mean Models for Estimation of Optimal Dynamic Treatment Regimes, Part I: Main Content (2010, positive): “…in that paper (and later exposed and specialized to many examples in a number of papers (e.g. Robins, Rotnitzky and Zhao, 1994, Robins, 1998 and 1999) and books (van der Laan and Robins, 2003, Tsiatis, 2006)) is di¢ cult to follow for the average reader of methodological statistical journals.”
Contrasting treatment-specific survival using double-robust estimators (2012, positive): “u/ with the first term being an IPTW estimator and the second term as the augmentation term [29].”
Maximum Likelihood Multiple Imputation: Faster Imputations and Consistent Standard Errors Without Posterior Draws (2012, neutral): “Clearly ŴMI is a consistent estimator of Vcom [25, 30].”
Improving efficiency and robustness of the doubly robust estimator for a population mean with incomplete data (2009, background): “From the point of view of semiparametric theory, the elements of the class of influence functions (Tsiatis, 2006, chapter 3) corresponding to estimators for μ of the form (5), with fully and correctly specified π(X ) but possibly incorrect m(X, β) and using β̂ converging in probability to some β∗,…”
Efficient semiparametric estimation of multi-valued treatment effects under ignorability (2010, neutral): “(A review and discussion of the links between these literatures may be found in Tsiatis (2006), 140 M.D. Cattaneo / Journal of Econometrics 155 (2010) 138–154 Bang and Robins (2005), Chen et al. (2005), Chen et al. (2004, 2008), and Wooldridge (2007), among others.)”