Toward a curse of dimensionality appropriate (CODA) asymptotic theory for semi-parametric models.

By James M. Robins, Yaacov Ritov. 1997

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

Approximate residual balancing: debiased inference of average treatment effects in high dimensions (2016, background): “…both weighting and regression adjustment are important is similar to conclusions drawn from the earlier literature on doubly robust estimation (e.g. Robins and Ritov (1997)), where combining both techniques was shown to extend the set of problems where efficient treatment effect estimation is…”
When to Control for Covariates? Panel Asymptotics for Estimates of Treatment Effects (2004, background): “…view that the imposition of restrictions on the propensity score lies at the heart of the propensity-score–covariatematching distinction.4 The two most commonly discussed parameters in evaluation studies are the effect of treatment on the treated 2 Robins and Ritov (1997) discuss a related problem.”
A Bayesian view of doubly robust causal inference (2016, background): “…or reweighting are not easy to interpret from the Bayesian perspective, since Bayesian inferences are naturally based on modelling of the outcome, with modelling of the treatment assignment playing no role in inference relating to the outcome/treatment relationship (Robins and Ritov, 1997).”
Challenges With Propensity Score Strategies in a High-Dimensional Setting and a Potential Alternative (2011, background): “…score literature (Rubin, 1973, 1979; Rubin & Thomas, 2000) and can be thought of as an approximation to more formal “double-robust” estimators (Robins & Ritov, 1997).4 Preretention reading, math, and general knowledge test scores, for example, are critical predictors in our analyses that we…”
Conditioning, Likelihood, and Coherence: A Review of Some Foundational Concepts (2000, methodology): “We summarize an example that was discussed in great detail by Robins and Ritov (1997).”
Bias-Reduced Doubly Robust Estimation (2015, background): “however is infeasible in realistic settings when the covariates contain multiple continuous components, because of the curse of dimensionality (Robins and Ritov 1997).”
Semiparametric Regression Analysis With Missing Response at Random (2003, background): “This is certainly a view commonly expressed in applied statistics; see, for example, Hastie and Tibshirani (1990) and Robins and Ritov (1997).”
Estimating and comparing time‐dependent areas under receiver operating characteristic curves for censored event times with competing risks (2013, background): “Although they could be extended to deal with censoring depending on several markers, using multidimensional kernels, their practical interest would be limited by the so-called curse of dimensionality phenomenon [34].”
Doubly Robust Estimation in Missing Data and Causal Inference Models (2005, background): “Formally, we are assuming that when there are missing data, the curse of dimensionality appropriate information bound for µ is zero ( Robins and Ritov, 1997 ).”
Double-Semiparametric Method for Missing Covariates in Cox Regression Models (2002, background): “But this approach rapidly becomes impractical with practical sample sizes as the dimension of Wc increases (see Robins and Ritov 1997 for a discussion of the curse of dimensionality in the missing-covariate problem).”
Bayesian Regression Tree Models for Causal Inference: Regularization, Confounding, and Heterogeneous Effects (with Discussion) (2020, unknown): “Finally, some have argued that a committed subjective Bayesian is specifically enjoined from encoding prior dependence on the propensity score in the outcome model based on philosophical considerations (Robins and Ritov, 1997).”
Structural nested models and G-estimation: the partially realized promise (2014, background): “…identification is of limited use in complex settings (especially with time-varying treatments considered subsequently), due to the curse of dimensionality (Robins and Ritov (1997)), it does ensure the ability to check the assumptions in any assumed causal model (provided a sufficient sample size).”
Calibrated Bayes (2006, background): “In a recent discussion of these ideas, Robins and Wasserman (2000) argued for reexamination of the likelihood principle in the context of an infinite-dimensional example described by Robins and Ritov (1997).”