Controlling Bias in Observational Studies: A Review

Cochran, William G.; Rubin, Donald B.

doi:10.1017/cbo9780511810725.005

Cited by 625 publications

(706 citation statements)

References 12 publications

Supporting

Mentioning

698

Contrasting

Unclassified

Order By: Relevance

“…Matching methods can be considered as one method for designing an observational study, in the sense of selecting the most appropriate data for reliable estimation of causal effects, as discussed in Cochran and Rubin (1973), Rubin (1977Rubin ( , 1997Rubin ( , 2004, Rosenbaum (1999Rosenbaum ( , 2002, and Heckman, Hidehiko, and Todd (1997). These papers stress the importance of carefully designing an observational study by making appropriate choices when it is impossible to have full control (e.g., randomization).…”

Section: Designing Observational Studiesmentioning

confidence: 99%

“…In fact, as discussed earlier, much research over a period of decades (Cochran & Rubin, 1973;Ho, Imai, King, & Stuart, 2007;Rubin, 1973bRubin, , 1979Rubin & Thomas, 2000) has shown that the best approach is to combine the two methods by, for example, doing regression adjustment on matched samples. Selecting matched samples reduces bias due to covariate differences, and regression analysis on those matched samples can adjust for small remaining differences and increase efficiency of estimates.…”

Section: Designing Observational Studiesmentioning

confidence: 99%

See 1 more Smart Citation

Best Practices in Quasi–Experimental Designs: Matching Methods for Causal Inference

Stuart¹,

Rubin²

2008

Best Practices in Quantitative Methods

262

203

View full text Add to dashboard Cite

Section: Designing Observational Studiesmentioning

confidence: 99%

Section: Designing Observational Studiesmentioning

confidence: 99%

Best Practices in Quasi–Experimental Designs: Matching Methods for Causal Inference

Stuart¹,

Rubin²

2008

Best Practices in Quantitative Methods

262

203

View full text Add to dashboard Cite

“…Two common approaches are propensity score matching (Rosenbaum and Rubin 1983) and multivariate matching based on Mahalanobis distance (Cochran and Rubin 1973;Rubin 1979Rubin , 1980. Matching methods based on the propensity score (estimated by logistic regression), Mahalanobis distance or a combination of the two have appealing theoretical properties if covariates have ellipsoidal distributions-e.g., distributions such as the normal or t. If the covariates are so distributed, these methods (more generally affinely invariant matching methods 4 ) have the property of "equal percent bias reduction" (EPBR) (Rubin 1976a,b;Rubin and Thomas 1992).…”

Section: Matching Methodsmentioning

confidence: 99%

“…The most common method of multivariate matching is based on Mahalanobis distance (Cochran and Rubin 1973;Rubin 1979Rubin , 1980. The Mahalanobis distance between any two column vectors is:…”

Section: Mahalanobis and Propensity Score Matchingmentioning

confidence: 99%

The Neyman— Rubin Model of Causal Inference and Estimation Via Matching Methods

Sekhon

2009

The Oxford Handbook of Political Methodology

View full text Add to dashboard Cite

This article presents a detailed discussion of the Neyman-Rubin model of causal inference. Additionally, it describes under what conditions ‘matching’ approaches can lead to valid inferences, and what kinds of compromises sometimes have to be made with respect to generalizability to ensure valid causal inferences. Moreover, the article summarizes Mill's first three canons and shows the importance of taking chance into account and comparing conditional probabilities when chance variations cannot be ignored. The significance of searching for causal mechanisms is often overestimated by political scientists and this sometimes leads to an underestimate of the importance of comparing conditional probabilities. The search for causal mechanisms is probably especially useful when working with observational data. Machine learning algorithms can be used against the matching problem.

show abstract

“…Section 3 presents the potential outcome framework and its associated Neyman's inference, and generalizes it to survival time outcomes. For non-censored real valued outcomes this approach has a long history for observational studies, see, e.g., Cochran and Rubin (1973), Rubin (1973aRubin ( , 1973bRubin ( , 1990b, and Rubin (1984, 1985). In Section 4 the treatment effects of interest are defined.…”

Section: Introductionmentioning

confidence: 99%

Non-parametric inference for the effect of a treatment on survival times with application in the health and social sciences

Luna

Johansson

2010

Journal of Statistical Planning and Inference

View full text Add to dashboard Cite

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. The Institute for the Study of Labor (IZA) in Bonn is a local and virtual international research center and a place of communication between science, politics and business. IZA is an independent nonprofit organization supported by Deutsche Post Foundation. The center is associated with the University of Bonn and offers a stimulating research environment through its international network, workshops and conferences, data service, project support, research visits and doctoral program. IZA engages in (i) original and internationally competitive research in all fields of labor economics, (ii) development of policy concepts, and (iii) dissemination of research results and concepts to the interested public. Terms of use: Documents in Non-Parametric Inference for the Effect of a Treatment on Survival Times with Application in the Health and Social Sciences Xavier de Luna Per Johansson D I S C U S S I O N P A P E R S E R I E SIZA Discussion Papers often represent preliminary work and are circulated to encourage discussion. Citation of such a paper should account for its provisional character. A revised version may be available directly from the author. In this paper we perform inference on the effect of a treatment on survival times in studies where the treatment assignment is not randomized and the assignment time is not known in advance. Two such studies are discussed: a heart transplant program and a study of Swedish unemployed eligible for employment subsidy. We estimate survival functions on a treated and a control group which are made comparable through matching on observed covariates. The inference is performed by conditioning on waiting time to treatment, that is time between the entrance in the study and treatment. This can be done only when sufficient data is available. In other cases, averaging over waiting times is a possibility, although the classical interpretation of the estimated survival functions is lost unless hazards are not functions of waiting time. To show unbiasedness and to obtain an estimator of the variance, we build on the potential outcome framework, which was introduced by J. Neyman in the context of randomized experiments, and adapted to observational studies by D. B. Rubin. Our approach does not make parametric or distributional assumptions. In particular, we do not assume proportionality of the hazards compared. Small sample performance of the estimator and a derived test of no treatment effect are studied in a Monte Carlo study. ...

show abstract

Controlling Bias in Observational Studies: A Review

Cited by 625 publications

References 12 publications

Best Practices in Quasi–Experimental Designs: Matching Methods for Causal Inference

Best Practices in Quasi–Experimental Designs: Matching Methods for Causal Inference

The Neyman— Rubin Model of Causal Inference and Estimation Via Matching Methods

Non-parametric inference for the effect of a treatment on survival times with application in the health and social sciences

Contact Info

Product

Resources

About