Adjusting for Confounding in Early Postlaunch Settings

Schmidt, Amand F.; Klungel, Olaf H.

doi:10.1097/ede.0000000000000388

Cited by 11 publications

(18 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The simplest method to estimate Ψ 0 is to use a logistic regression model fitted in the unexposed population, regressing the observed outcome on baseline covariates. The use of an independent set of unexposed subjects (as opposed to the ‘same‐sample’ estimation) has also been described for this step . The use of the full sample (instead of the unexposed subgroup only) leads to the estimation of Miettinen's multivariate confounder score , which may be less robust to model misspecification than Hansen's PGS .…”

Section: Methodsmentioning

confidence: 99%

“…If we restrict our discussion to Hansen's definition of the PGS, to our knowledge, five simulation studies have evaluated the performance of PGS‐based methods: Arbogast et al , Leacy and Stuart , Wyss et al , Pfeiffer and Riedl and Schmidt et al . The first two focused on a collapsible measure of treatment effect.…”

Section: Propensity and Prognostic Scores Overviewmentioning

confidence: 99%

See 1 more Smart Citation

Estimation of conditional and marginal odds ratios using the prognostic score

et al. 2016

View full text Add to dashboard Cite

Introduced by Hansen in 2008, the prognostic score (PGS) has been presented as 'the prognostic analogue of the propensity score' (PPS). PPS-based methods are intended to estimate marginal effects. Most previous studies evaluated the performance of existing PGS-based methods (adjustment, stratification and matching using the PGS) in situations in which the theoretical conditional and marginal effects are equal (i.e., collapsible situations). To support the use of PGS framework as an alternative to the PPS framework, applied researchers must have reliable information about the type of treatment effect estimated by each method. We propose four new PGS-based methods, each developed to estimate a specific type of treatment effect. We evaluated the ability of existing and new PGS-based methods to estimate the conditional treatment effect (CTE), the (marginal) average treatment effect on the whole population (ATE), and the (marginal) average treatment effect on the treated population (ATT), when the odds ratio (a non-collapsible estimator) is the measure of interest. The performance of PGS-based methods was assessed by Monte Carlo simulations and compared with PPS-based methods and multivariate regression analysis. Existing PGS-based methods did not allow for estimating the ATE and showed unacceptable performance when the proportion of exposed subjects was large. When estimating marginal effects, PPS-based methods were too conservative, whereas the new PGS-based methods performed better with low prevalence of exposure, and had coverages closer to the nominal value. When estimating CTE, the new PGS-based methods performed as well as traditional multivariate regression. Copyright © 2016 John Wiley & Sons, Ltd.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Propensity and Prognostic Scores Overviewmentioning

confidence: 99%

Estimation of conditional and marginal odds ratios using the prognostic score

et al. 2016

View full text Add to dashboard Cite

show abstract

“…In these settings, penalized models, using for example a Firth 27 , 28 or Lasso 29 penalization, are expected to perform better. 30 Finally, random effects or fixed effect analysis models were used depending on whether the simulation scenario included between-study variance or not. 31 In empirical analyses, the choice between random effects and fixed effect models typically depends on a heterogeneity measure.…”

Section: Discussionmentioning

confidence: 99%

Comparison of variance estimators for meta-analysis of instrumental variable estimates

Schmidt

Hingorani

Jefferis³

et al. 2016

Int. J. Epidemiol.

View full text Add to dashboard Cite

Background: Mendelian randomization studies perform instrumental variable (IV) analysis using genetic IVs. Results of individual Mendelian randomization studies can be pooled through meta-analysis. We explored how different variance estimators influence the meta-analysed IV estimate. Methods: Two versions of the delta method (IV before or after pooling), four bootstrap estimators, a jack-knife estimator and a heteroscedasticity-consistent (HC) variance estimator were compared using simulation. Two types of meta-analyses were compared, a two-stage meta-analysis pooling results, and a one-stage meta-analysis pooling datasets. Results: Using a two-stage meta-analysis, coverage of the point estimate using bootstrapped estimators deviated from nominal levels at weak instrument settings and/or outcome probabilities ≤ 0.10. The jack-knife estimator was the least biased resampling method, the HC estimator often failed at outcome probabilities ≤ 0.50 and overall the delta method estimators were the least biased. In the presence of between-study heterogeneity, the delta method before meta-analysis performed best. Using a one-stage meta-analysis all methods performed equally well and better than two-stage meta-analysis of greater or equal size. Conclusions: In the presence of between-study heterogeneity, two-stage meta-analyses should preferentially use the delta method before meta-analysis. Weak instrument bias can be reduced by performing a one-stage meta-analysis.

show abstract

“…However, even in a large sample setting, we may face the challenge of rare exposure (or treatment). The disease risk score (DRS) method is suitable to use under these circumstances, such as in the early market phase of a drug when reduction in confounder dimensions is likely important 47–49. DRS is comparable to PS in so far that information from several variables is summarized in one single score.…”

Section: Ps – Our Main Response To Confounding?mentioning

confidence: 99%

Control of confounding in the analysis phase – an overview for clinicians

Kahlert¹,

Gribsholt²,

Gammelager³

et al. 2017

CLEP

105

View full text Add to dashboard Cite

In observational studies, control of confounding can be done in the design and analysis phases. Using examples from large health care database studies, this article provides the clinicians with an overview of standard methods in the analysis phase, such as stratification, standardization, multivariable regression analysis and propensity score (PS) methods, together with the more advanced high-dimensional propensity score (HD-PS) method. We describe the progression from simple stratification confined to the inclusion of a few potential confounders to complex modeling procedures such as the HD-PS approach by which hundreds of potential confounders are extracted from large health care databases. Stratification and standardization assist in the understanding of the data at a detailed level, while accounting for potential confounders. Incorporating several potential confounders in the analysis typically implies the choice between multivariable analysis and PS methods. Although PS methods have gained remarkable popularity in recent years, there is an ongoing discussion on the advantages and disadvantages of PS methods as compared to those of multivariable analysis. Furthermore, the HD-PS method, despite its generous inclusion of potential confounders, is also associated with potential pitfalls. All methods are dependent on the assumption of no unknown, unmeasured and residual confounding and suffer from the difficulty of identifying true confounders. Even in large health care databases, insufficient or poor data may contribute to these challenges. The trend in data collection is to compile more fine-grained data on lifestyle and severity of diseases, based on self-reporting and modern technologies. This will surely improve our ability to incorporate relevant confounders or their proxies. However, despite a remarkable development of methods that account for confounding and new data opportunities, confounding will remain a serious issue. Considering the advantages and disadvantages of different methods, we emphasize the importance of the clinical input and of the interplay between clinicians and analysts to ensure a proper analysis.

show abstract

Adjusting for Confounding in Early Postlaunch Settings

Cited by 11 publications

References 41 publications

Estimation of conditional and marginal odds ratios using the prognostic score

Estimation of conditional and marginal odds ratios using the prognostic score

Comparison of variance estimators for meta-analysis of instrumental variable estimates

Control of confounding in the analysis phase – an overview for clinicians

Contact Info

Product

Resources

About

Adjusting for Confounding in Early Postlaunch Settings

Cited by 11 publications

References 41 publications

Estimation of conditional and marginal odds ratios using the prognostic score

Estimation of conditional and marginal odds ratios using the prognostic score

Comparison of variance estimators for meta-analysis of instrumental variable estimates

Control of confounding in the analysis phase &ndash; an overview for clinicians

Contact Info

Product

Resources

About

Control of confounding in the analysis phase – an overview for clinicians