Observational Studies

By J. Hallas. 2003

Subfields: Statistics and Probability, Causal Inference & Discovery

How researchers see this paper

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

In Statistics and Probability

In Causal Inference & Discovery

Citations in the corpus

Deep Kalman Filters (2015, background): “For a general introduction to estimating expected counterfactual effects over a population - see Morgan & Winship (2014); H ¨ oﬂer (2005); Rosenbaum (2002).”
Recommendations as Treatments: Debiasing Learning and Evaluation (2016, methodology): “Propensity Estimation via Logistic Regression The second propensity estimation approach we explore (which does not require a sample of MCAR data) is based on logistic regression and is commonly used in causal inference (Rosenbaum, 2002).”
Causal Inference through a Witness Protection Program (2014, background): “Such covariate sets are often found in real-world problems, and form the basis of many of the observational studies done in practice (Rosenbaum, 2002a).”
The Econometrics of Randomized Experiments (2016, methodology): “The alternative, where parts of the assignment mechanism are unknown, and may possibly depend on unobserved characteristics (including the potential outcomes) of the units, are referred to as observational studies (Cochran, 1972).”
The State of Applied Econometrics - Causality and Policy Evaluation (2016, positive): “Following Rosenbaum and Rubin [1983a] a large literature focused on estimation of the population average treatment effect τ = E[Yi(1) − Yi(0)], under the unconfoundedness assumption that”
Approximate residual balancing: debiased inference of average treatment effects in high dimensions (2016, background): “…matching, propensity score weighting and subclassification, as well as doubly robust combinations thereof (e.g. Abadie and Imbens (2006), Heckman et al. (1998), Hirano et al. (2003), Robins et al. (1994, 1995, 2017), Rosenbaum (2002), Tan (2010), Tsiatis (2007) and Van Der Laan and Rubin (2006)).”
Learning Representations for Counterfactual Inference (2016, methodology): “The methods include nearest-neighbor matching, propensity score matching, and propensity score re-weighting (Rosen-baum & Rubin, 1983; Rosenbaum, 2002; Austin, 2011).”
Causal inference in statistics: An overview (2009, background): “Paul Rosenbaum, for example, writes: “there is little or no reason to avoid adjustment for a true covariate, a variable describing subjects before treatment” (Rosenbaum, 2002, p. 76).”
Comment: Demystifying Double Robustness: A Comparison of Alternative Strategies for Estimating a Population Mean from Incomplete Data. (2008, background): “Our second purpose is to investigate the practical behavior of these estimators not only when either of the underlying models is correct, but in a scenario where both models are moderately misspecified.”
The Selective Labels Problem: Evaluating Algorithmic Predictions in the Presence of Unobservables (2017, methodology): “(2) non-parametric methods such as propensity score matching, nearest-neighbor matching, which do not explicitly model the relationship between observed features, treatments, and outcomes [4, 15, 35, 36, 41].”
Automated versus Do-It-Yourself Methods for Causal Inference: Lessons Learned from a Data Analysis Competition (2017, background): “…assumption (Rubin, 1978), which is also known as “selection on observables,” “all confounders measured,” “exchangeability,” the “conditional independence assumption” and “no hidden bias” (see Barnow, Cain and Goldberger, 1980; Greenland and Robins, 1986; Lechner, 2001; Rosenbaum, 2002).”
Education and Human Capital Externalities: Evidence from Colonial Benin (2015, methodology): “The details of the framework can be found in Rosenbaum (2002).”
Evaluating Kindergarten Retention Policy (2006, result): “…was significantly different from 0, we examined whether our conclusion would be altered by additional adjustment for unmeasured confounders, the omission of which would create a bias comparable to that of the most important observed covariates (Lin, Psaty, and Kronmal 1998; Rosenbaum 1986, 2002).”
Decomposing Treatment Effect Variation (2016, methodology): “First, we take a fully randomization-based perspective (see Rosenbaum 2002; Imbens and Rubin 2015), and propose estimators that are entirely justified by the randomization itself.”
DOES MARRIAGE REDUCE CRIME? A COUNTERFACTUAL APPROACH TO WITHIN‐INDIVIDUAL CAUSAL EFFECTS* (2006, methodology): “Applying the stable unit treatment value assumption (SUTVA; see Rosenbaum, 2002), we make the reasonable assumption of no interaction across units—one man's response to marriage is not conceived as dependent on another subject's response.”