Propensity score models in observational comparative effectiveness studies: cornerstone of design or statistical afterthought?
2
Citation
25
Reference
10
Related Paper
Citation Trend
Abstract:
Propensity score models are increasingly used in observational comparative effectiveness studies to reduce confounding by covariates that are associated with both a study outcome and treatment choice. Any such potentially confounding covariate will bias estimation of the effect of treatment on the outcome, unless the distribution of that covariate is well-balanced between treatment and control groups. Constructing a subsample of treated and control subjects who are matched on estimated propensity scores is a means of achieving such balance for covariates that are included in the propensity score model. If, during study design, investigators assemble a comprehensive inventory of known and suspected potentially confounding covariates, examination of how well this inventory is covered by the chosen dataset yields an assessment of the extent of bias reduction that is possible by matching on estimated propensity scores. These considerations are explored by examining the designs of three recently published comparative effectiveness studies.Keywords:
Comparative effectiveness research
Cite
This chapter explores the important issue of confounding in observational studies. The potential imbalances that result for not controlling assignment of treatment or exposure may lead to imbalance of variables that are associated with both treatment and intervention (or exposure) thus confounding results. Therefore, in this context, a potential relationship between an intervention and an outcome could be invalid. This chapter therefore explains basic definitions of confounding and presents some methods to control for confounders, highlighting the use of the propensity score, which is considered a robust method for this purpose. Different techniques of adjustment using propensity score (matching, stratification, regression, and weighting) are also discussed. This chapter concludes with a case discussion about confounding and how to address it.
Cite
Citations (0)
The inverse probability weighting is an important propensity score weighting method to estimate the average treatment effect. Recent literature shows that it can be easily combined with covariate balancing constraints to reduce the detrimental effects of excessively large weights and improve balance. Other methods are available to derive weights that balance covariate distributions between the treatment groups without the involvement of propensity scores. We conducted comprehensive Monte Carlo experiments to study whether the use of covariate balancing constraints circumvent the need for correct propensity score model specification, and whether the use of a propensity score model further improves the estimation performance among methods that use similar covariate balancing constraints. We compared simple inverse probability weighting, two propensity score weighting methods with balancing constraints (covariate balancing propensity score, covariate balancing scoring rule), and two weighting methods with balancing constraints but without using the propensity scores (entropy balancing and kernel balancing). We observed that correct specification of the propensity score model remains important even when the constraints effectively balance the covariates. We also observed evidence suggesting that, with similar covariate balance constraints, the use of a propensity score model improves the estimation performance when the dimension of covariates is large. These findings suggest that it is important to develop flexible data-driven propensity score models that satisfy covariate balancing conditions.
Inverse probability weighting
Cite
Citations (24)
Inverse probability weighting
Marginal structural model
Cite
Citations (565)
Cite
Citations (4)
Cite
Citations (0)
Cite
Citations (0)
A propensity score is the probability of being treated or exposed, given measured confounders such as age. Propensity score methods can control for measured confounders in observational research, but not for unmeasured confounders. Study participants with the same propensity score will, on average, have a similar distribution of measured confounders. The propensity score can be used to control for confounding by means of stratification, matching, including the propensity score as a covariate in a multivariable regression model, or by weighting the study population using the propensity score. Propensity score methods can often control for more confounders than other methods, particularly in the case of a rare outcome. Reports on propensity score methods should mention which confounders were included in the propensity score and to what extent confounders were balanced across study groups, after stratification based on the propensity score.
Cite
Citations (7)
Abstract Confounding variables can affect the results from studies of children with Down syndrome and their families. Traditional methods for addressing confounders are often limited, providing control for only a few confounding variables. This study introduces propensity score matching to control for multiple confounding variables. Using Tennessee birth data as an example, newborns with Down syndrome were compared with a group of typically developing infants on birthweight. Three approaches to matching on confounders—nonmatched, covariate matched, and propensity matched—were compared using 8 potential confounders. Fewer than half of the newborns with Down syndrome were matched using covariate matching, and the matched group was differed from the unmatched newborns. Using propensity scores, 100% of newborns with Down syndrome could be matched to a group of comparison newborns, a decreased effect size was found on newborn birthweight, and group differences were not statistically significant.
Cite
Citations (24)
Abstract In epidemiologic studies of the effect of an exposure on disease, the crude association of exposure with disease may fail to reflect a causal association due to confounding by one or more covariates. Most previous discussions of confounding in the epidemiologic literature have considered only point exposure studies, that is, studies that measure exposure and covariate status only once, at start of follow‐up. In this paper we offer definitions of confounding suitable for longitudinal studies that obtain data on exposure, covariate, and vital status at several points in time. An important difference between longitudinal studies and point exposure studies is that, in longitudinal studies, a time‐dependent covariate can be simultaneously a confounder and an intermediate variable on the causal pathway from exposure to disease. In this paper I propose an estimator, the extended standardized risk difference, that provides control for confounding by a covariate that is simultaneously a confounder and an intermediate variable.
Cite
Citations (244)
In this article, we presented the rationale and calculation procedures of the propcnsity score matching (PSM), and its application in the designing stage of an cpidcrniological study. Based on existing observational data, PSM can be used to select one or more comparable controls for each subject in 'treatment' group according to the propensity scores estimated by 'treatment' variable and main covariates. The results of an example analysis showed that the bias for main confounders between the treated and control samples declined more than 55% after PMS. Conclusion: PSM can reduce most of the confounding bias of the observational study, and can obtain approximate study effect to the randomized controlled trials when used in the designing of thc cpidcmiological study.
Key words:
Propensity score matching; Confounding bias; Epidemiology
Cite
Citations (2)