Application of propensity score matching in the design of an epidemiological study
2
Citation
0
Reference
20
Related Paper
Citation Trend
Abstract:
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; EpidemiologyAbstract This article uses propensity score methods to estimate the treatment impact of the National Supported Work (NSW) Demonstration, a labor training program, on postintervention earnings. We use data from Lalonde's evaluation of nonexperimental methods that combine the treated units from a randomized evaluation of the NSW with nonexperimental comparison units drawn from survey datasets. We apply propensity score methods to this composite dataset and demonstrate that, relative to the estimators that Lalonde evaluates, propensity score estimates of the treatment impact are much closer to the experimental benchmark estimate. Propensity score methods assume that the variables associated with assignment to treatment are observed (referred to as ignorable treatment assignment, or selection on observables). Even under this assumption, it is difficult to control for differences between the treatment and comparison groups when they are dissimilar and when there are many preintervention variables. The estimated propensity score (the probability of assignment to treatment, conditional on preintervention variables) summarizes the preintervention variables. This offers a diagnostic on the comparability of the treatment and comparison groups, because one has only to compare the estimated propensity score across the two groups. We discuss several methods (such as stratification and matching) that use the propensity score to estimate the treatment impact. When the range of estimated propensity scores of the treatment and comparison groups overlap, these methods can estimate the treatment impact for the treatment group. A sensitivity analysis shows that our estimates are not sensitive to the specification of the estimated propensity score, but are sensitive to the assumption of selection on observables. We conclude that when the treatment and comparison groups overlap, and when the variables determining assignment to treatment are observed, these methods provide a means to estimate the treatment impact. Even though propensity score methods are not always applicable, they offer a diagnostic on the quality of nonexperimental comparison groups in terms of observable preintervention variables. Key Words: MatchingProgram evaluationPropensity score.
Average treatment effect
Comparability
Treatment effect
Cite
Citations (455)
Background: Lack of randomization of nursing intervention in outcome effectiveness studies may lead to imbalanced covariates. Consequently, estimation of nursing intervention effect can be biased as in other observational studies. Propensity score analysis is an effective statistical method to reduce such bias and further derive causal effects in observational studies. Objectives: The objective of this study was to illustrate the use of propensity score analysis in quantitative nursing research through an example of pain management effect on length of hospital stay. Methods: Propensity scores are generated through a regression model treating the nursing intervention as the dependent variable and all confounding covariates as predictor variables. Then, propensity scores are used to adjust for this nonrandomized assignment of nursing intervention through three approaches: regression covariance adjustment, stratification, and matching in the predictive outcome model for nursing intervention. Results: Propensity score analysis reduces the confounding covariates into a single variable of propensity score. After stratification and matching on propensity scores, observed covariates between nursing intervention groups are more balanced within each stratum or in the matched samples. The likelihood of receiving pain management is accounted for in the outcome model through the propensity scores. Both regression covariance adjustment and matching methods report a significant pain management effect on length of hospital stay in this example. The pain management effect can be regarded as causal when the strongly ignorable treatment assignment assumption holds. Discussion: Propensity score analysis provides an alternative statistical approach to the classical multivariate regression, stratification, and matching techniques for examining the effects of nursing intervention with a large number of confounding covariates in the background. It can be used to derive causal effects of nursing intervention in observational studies under certain circumstances.
Cite
Citations (39)
Propensity score methods are increasingly being used to estimate causal treatment effects in observational studies. In medical and epidemiological studies, outcomes are frequently time‐to‐event in nature. Propensity‐score methods are often applied incorrectly when estimating the effect of treatment on time‐to‐event outcomes. This article describes how two different propensity score methods (matching and inverse probability of treatment weighting) can be used to estimate the measures of effect that are frequently reported in randomized controlled trials: (i) marginal survival curves, which describe survival in the population if all subjects were treated or if all subjects were untreated; and (ii) marginal hazard ratios. The use of these propensity score methods allows one to replicate the measures of effect that are commonly reported in randomized controlled trials with time‐to‐event outcomes: both absolute and relative reductions in the probability of an event occurring can be determined. We also provide guidance on variable selection for the propensity score model, highlight methods for assessing the balance of baseline covariates between treated and untreated subjects, and describe the implementation of a sensitivity analysis to assess the effect of unmeasured confounding variables on the estimated treatment effect when outcomes are time‐to‐event in nature. The methods in the paper are illustrated by estimating the effect of discharge statin prescribing on the risk of death in a sample of patients hospitalized with acute myocardial infarction. In this tutorial article, we describe and illustrate all the steps necessary to conduct a comprehensive analysis of the effect of treatment on time‐to‐event outcomes. © 2013 The authors. Statistics in Medicine published by John Wiley & Sons, Ltd.
Marginal structural model
Inverse probability weighting
Average treatment effect
Cite
Citations (1,220)
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.
Comparative effectiveness research
Cite
Citations (2)
The propensity score is defined as the probability of each individual study subject being assigned to a group of interest for comparison purposes.Propensity score adjustment is a method of ensuring an even distribution of confounders between groups, thereby increasing between group comparability.Propensity score analysis is therefore an increasingly applied statistical method in observational studies.The purpose of this article was to provide a step-by-step nonmathematical conceptual guide to propensity score analysis with particular emphasis on propensity score matching.A software program code used for propensity score matching was also presented.
Comparability
Cite
Citations (174)
In the analysis of observational data, stratifying patients on the estimated propensity scores reduces confounding from measured variables. Confidence intervals for the treatment effect are typically calculated without acknowledging uncertainty in the estimated propensity scores, and intuitively this may yield inferences, which are falsely precise. In this paper, we describe a Bayesian method that models the propensity score as a latent variable. We consider observational studies with a dichotomous treatment, dichotomous outcome, and measured confounders where the log odds ratio is the measure of effect. Markov chain Monte Carlo is used for posterior simulation. We study the impact of modelling uncertainty in the propensity scores in a case study investigating the effect of statin therapy on mortality in Ontario patients discharged from hospital following acute myocardial infarction. Our analysis reveals that the Bayesian credible interval for the treatment effect is 10 per cent wider compared with a conventional propensity score analysis. Using simulations, we show that when the association between treatment and confounders is weak, then this increases uncertainty in the estimated propensity scores. Bayesian interval estimates for the treatment effect are longer on average, though there is little improvement in coverage probability. A novel feature of the proposed method is that it fits models for the treatment and outcome simultaneously rather than one at a time. The method uses the outcome variable to inform the fit of the propensity model. We explore the performance of the estimated propensity scores using cross-validation.
Credible interval
Cite
Citations (0)
Propensity score matching (PSM) is a commonly used statistical method in orthopedic surgery research that accomplishes the removal of confounding bias from observational cohorts where the benefit of randomization is not possible. An alternative to multiple regression analysis, PSM attempts to reduce the effects of confounders by matching already treated subjects with control subjects who exhibit a similar propensity for treatment based on preexisting covariates that influence treatment selection. It, therefore, establishes a new control group by discarding outlier control subjects. This new control group reduces the unwanted influences of covariates, allowing for proper measurement of the intended variable. An example from orthopedic spine literature is discussed to illustrate how PSM may be applied in practice. PSM is uniquely valuable in its utility and simplicity, but it is limited in that it requires the removal of data and works primarily on binary treatments. In addition to matching, the propensity score can be used for stratification, covariate adjustments, and inverse probability of treatment weighting, but these topics are outside the scope of this paper. Personnel in the orthopedic field would benefit from learning about the function and application of this method given its common use in the orthopedic literature.
Inverse probability weighting
Cite
Citations (441)
Average treatment effect
Cite
Citations (6)
Direct comparisons of health-related quality of life (HRQoL) outcomes between non-randomized groups might be biased, as outcomes are confounded by imbalance in pre-treatment patient characteristics. Such bias can be reduced by adjusting on observed covariates. This is the setting of HRQoL comparisons with reference data, where age and gender adjustment is commonly used for this purpose. However, other observed covariates can be used to lessen this bias and yield more precise estimates. The objective of this study is to show that more accurate HRQoL comparisons with reference data can be obtained, accounting for few covariates in addition to age and gender by a propensity score matching approach.
Average treatment effect
Cite
Citations (5)
Background Confounding by indication is a common problem in pharmacoepidemiology, where predictors of treatment also have prognostic value for the outcome of interest. The tools available to the epidemiologist that can be used to mitigate the effects of confounding by indication often have limits with respect to the number of variables that can be simultaneously incorporated as components of the confounding. This constraint becomes particularly apparent in the context of a rich data source (such as administrative claims data), applied to the study of an outcome that occurs infrequently. In such settings, there will typically be many more variables available for control as potential confounders than traditional epidemiologic techniques will allow. Methods One tool that can indirectly permit control of a large number of variables is the propensity score approach. This paper illustrates the application of the propensity score to a study conducted in an administrative database, and raises critical issues to be addressed in such an analysis. In this example, the effect of statin therapy on the occurrence of myocardial infarction was examined, and numerous potential confounders of this association were adjusted simultaneously using a propensity score to form matched cohorts of statin initiators and non-initiators. Results The incidence of myocardial infarction observed in the statin treated cohort was lower than the incidence in the untreated cohort, and the magnitude of this effect was consistent with results from randomized placebo controlled clinical trials of statin therapy. Conclusions This example illustrates how confounding by indication can be mitigated by the propensity score matching technique. Concerns remain over the generalizability of estimates obtained from such a study, and how to know when propensity scores are removing bias, since apparent balance between compared groups on measured variables could leave variables not included in the propensity score unbalanced and lead to confounded effect estimates. Copyright © 2005 John Wiley & Sons, Ltd.
Pharmacoepidemiology
Cite
Citations (202)