Accuracy of Conventional and Marginal Structural Cox Model Estimators: A Simulation Study

Xiao, Yongling; Abrahamowicz, Michał; Moodie, Erica E. M.

doi:10.2202/1557-4679.1208

Cited by 68 publications

(85 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To estimate the marginal causal effect of RRT on mortality, we used a marginal structural Cox model [34,35] in which each patient was assigned a likelihood weight of RRT using the inverse-probability-oftreatment-weighted (IPTW) estimator.…”

Section: Discussionmentioning

confidence: 99%

Acute kidney injury in critical care: Experience of a conservative strategy

Gaudry¹,

Ricard²,

Leclaire³

et al. 2014

Journal of Critical Care

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Acute kidney injury in critical care: Experience of a conservative strategy

Gaudry¹,

Ricard²,

Leclaire³

et al. 2014

Journal of Critical Care

View full text Add to dashboard Cite

“…In the class of the missed visits scenarios, methods of (i) weights truncation at first and 99th centiles and (ii) weights normalization was applied to adjust for extremely large treatment weights due to violation of the positivity assumption. Normalized weights were created as sw m ×N(m)/ m j=1 sw j , where N(m) is the number of individuals at risk at time m (Xiao et al, 2010).…”

Section: Methods Of Analysismentioning

confidence: 99%

Performance of the marginal structural models under various scenarios of incomplete marker's values: A simulation study

Vourli¹,

Touloumi²

2014

Biometrical J

View full text Add to dashboard Cite

Marginal structural models (MSMs) have been proposed for estimating a treatment's effect, in the presence of time-dependent confounding. We aimed to evaluate the performance of the Cox MSM in the presence of missing data and to explore methods to adjust for missingness. We simulated data with a continuous time-dependent confounder and a binary treatment. We explored two classes of missing data: (i) missed visits, which resemble clinical cohort studies; (ii) missing confounder's values, which correspond to interval cohort studies. Missing data were generated under various mechanisms. In the first class, the source of the bias was the extreme treatment weights. Truncation or normalization improved estimation. Therefore, particular attention must be paid to the distribution of weights, and truncation or normalization should be applied if extreme weights are noticed. In the second case, bias was due to the misspecification of the treatment model. Last observation carried forward (LOCF), multiple imputation (MI), and inverse probability of missingness weighting (IPMW) were used to correct for the missingness. We found that alternatives, especially the IPMW method, perform better than the classic LOCF method. Nevertheless, in situations with high marker's variance and rarely recorded measurements none of the examined method adequately corrected the bias.

show abstract

“…Marginal structural models are typically fitted using inverse probability weighting (Robins 2000a;Hernan et al 2000;Xiao, Abrahamowicz, and Moodie 2010). We carried out a simulation study designed to demonstrate an application of TMLE and IPTW to estimating the parameter of an MSM under two different data generating distributions.…”

Section: Comparison Of Estimatorsmentioning

confidence: 99%

tmle: AnRPackage for Targeted Maximum Likelihood Estimation

2012

View full text Add to dashboard Cite

Targeted maximum likelihood estimation (TMLE) is a general approach for constructing an efficient double-robust semi-parametric substitution estimator of a causal effect parameter or statistical association measure. tmle is a recently developed R package that implements TMLE of the effect of a binary treatment at a single point in time on an outcome of interest, controlling for user supplied covariates, including an additive treatment effect, relative risk, odds ratio, and the controlled direct effect of a binary treatment controlling for a binary intermediate variable on the pathway from treatment to the outcome. Estimation of the parameters of a marginal structural model is also available. The package allows outcome data with missingness, and experimental units that contribute repeated records of the point-treatment data structure, thereby allowing the analysis of longitudinal data structures. Relevant factors of the likelihood may be modeled or fit data-adaptively according to user specifications, or passed in from an external estimation procedure. Effect estimates, variances, p values, and 95% confidence intervals are provided by the software.

show abstract

Accuracy of Conventional and Marginal Structural Cox Model Estimators: A Simulation Study

Cited by 68 publications

References 15 publications

Acute kidney injury in critical care: Experience of a conservative strategy

Acute kidney injury in critical care: Experience of a conservative strategy

Performance of the marginal structural models under various scenarios of incomplete marker's values: A simulation study

tmle: AnRPackage for Targeted Maximum Likelihood Estimation

Contact Info

Product

Resources

About