Analysis of Semiparametric Regression Models for Repeated Outcomes in the Presence of Missing Data

Robins, James M.; Rotnitzky, Andrea; Zhao, Lue Ping

doi:10.1080/01621459.1995.10476493

Cited by 1,204 publications

(862 citation statements)

References 35 publications

Supporting

Mentioning

853

Contrasting

Unclassified

Order By: Relevance

“…Initially proposed by Rosenbaum (1987) for binary treatments, elaborated by Robins and colleagues (Robins, 2000;Robins & Rotnitzky, 1995), and considered a strategy for evaluating multivalued treatments (Imbens, 2000;Robins, Hernan, & Siebert, 2003), IPTW assigns to each unit a weight that is exactly reciprocal to the unit's propensity of receiving the treatment actually received. We argue that the MMW-S strategy often outperforms the IPTW method because the former combines some important strength of propensity score stratification and IPTW.…”

Section: Introductionmentioning

confidence: 99%

Marginal Mean Weighting Through Stratification: Adjustment for Selection Bias in Multilevel Data

Hong

2010

Journal of Educational and Behavioral Statistics

113

130

View full text Add to dashboard Cite

Defining causal effects as comparisons between marginal population means, this article introduces marginal mean weighting through stratification (MMW-S) to adjust for selection bias in multilevel educational data. The article formally shows the inherent connections among the MMW-S method, propensity score stratification, and inverse-probability-of-treatment weighting (IPTW). Both MMW-S and IPTW are suitable for evaluating multiple concurrent treatments and hence have broader applications than matching, stratification, or covariance adjustment for the propensity score. Furthermore, mathematical consideration and a series of simulations reveal that the MMW-S method has incorporated some important strengths of the propensity score stratification method, which generally enhance the robustness of MMW-S estimates in comparison with IPTW estimates. To illustrate, the author applies the MMW-S method to evaluations of within-class homogeneous grouping in early elementary reading instruction.

show abstract

Section: Introductionmentioning

confidence: 99%

Marginal Mean Weighting Through Stratification: Adjustment for Selection Bias in Multilevel Data

Hong

2010

Journal of Educational and Behavioral Statistics

113

130

View full text Add to dashboard Cite

show abstract

“…A disadvantage of GEE is that it assumes that missingness is 'completely at random', which is often not the case (25) and can lead to bias when missingness is related to outcome (Figure 4). An extension of GEE, GEE with inverse probability weights (27,28), can deal with missing data that are not completely at random, but this extension is not readily available in standard software packages. Furthermore, GEE is often less precise than a multivariate normal regression.…”

Section: Discussionmentioning

confidence: 98%

Comparison of methodologies for analysing the progression of joint destruction in rheumatoid arthritis

Knevel

Tsonaka

Cessie

et al. 2013

Scandinavian Journal of Rheumatology

View full text Add to dashboard Cite

show abstract

“…Inverse weighted estimating functions are perhaps most widely adopted for semiparametric analyses, and much of the literature is devoted to "missing at random" mechanisms [38]. In this context, these weights are estimated by modeling the conditional probability of remaining in the study until the next visit given completion of the current visit and the observed "history" [39,40]. Less attention has been directed to the setting in which no visit schedule is planned and assessments happen in a "fully stochastic" fashion.…”

Section: Discussionmentioning

confidence: 99%

“…The following derivation is based on the general theory layed out by Newey and McFadden [54] and Robins et al [39]. Here, we introduce a subscript i to index individuals because we must compute empirical averages over individuals for variance estimation.…”

Section: Appendix B Derivation Of Asymptotic Variance From Weighted Amentioning

confidence: 99%

Inverse probability weighted estimating equations for randomized trials in transfusion medicine

Cook

Lee

Cuerden

et al. 2013

Statistics in Medicine

View full text Add to dashboard Cite

SummaryThrombocytopenia is a condition characterized by extremely low platelet counts, which puts patients at elevated risk of morbidity and mortality because of bleeding. Trials in transfusion medicine are routinely designed to assess the effect of experimental platelet products on patients platelet counts. In such trials, patients may receive multiple platelet transfusions over a predefined period of treatment, and a response is available from each such administration. The resulting data comprised multiple responses per patient, and although it is natural to want to use this data in testing for treatment effects, naive analyses of the multiple responses can yield biased estimates of the probability of response and associated treatment effects. These biases arise because only subsets of the patients randomized contribute response data on the second and subsequent administrations of therapy and the balance between treatment groups with respect to potential confounding factors is lost. We discuss the design and analysis issues involved in this setting and make recommendations for the design of future platelet transfusion trials.

show abstract

Analysis of Semiparametric Regression Models for Repeated Outcomes in the Presence of Missing Data

Cited by 1,204 publications

References 35 publications

Marginal Mean Weighting Through Stratification: Adjustment for Selection Bias in Multilevel Data

Marginal Mean Weighting Through Stratification: Adjustment for Selection Bias in Multilevel Data

Comparison of methodologies for analysing the progression of joint destruction in rheumatoid arthritis

Inverse probability weighted estimating equations for randomized trials in transfusion medicine

Contact Info

Product

Resources

About