Contents
How is the propensity score used in regression?
Propensity score methods are commonly used to adjust for observed confounding when estimating the conditional treatment effect in observational studies. One popular method, covariate adjustment of the propensity score in a regression model, has been empirically shown to be biased in non-linear models.
Which is better, a propensity score or a covariate?
Propensity scores (PS) are an increasingly popular method to adjust for confounding in observational studies. Propensity score methods have theoretical advantages over conventional covariate adjustment, but their relative performance in real-word scenarios is poorly characterized.
Can a regression model be used to match patients?
The matching can be done either on covariate values themselves (eg, treated and untreated patients are matched on gender, age, and disease stage) or based on a propensity score [1]. In the latter approach, the first step involves building a logistic regression model to predict the probability of receiving treatment, given a set of covariates.
Which is a benefit of matching over regression?
All the other assumptions are essentially the same between regression and matching. The benefit of matching over regression is that it is non-parametric (except you do have to assume that you have the right propensity score, if that is how you are doing your matching).
REGRESSION ADJUSTMENT USING THE PROPENSITY SCORE. A third method is regression adjustment, also proposed in the initial paper by Rosenbaum and Rubin (1983). In this method the propensity score is calculated, as before, and is simply used as an additional covariate in the outcome model.
How is the inverse of the propensity score used?
Here, the inverse of the propensity score is used to weight each observation in the treated group, and one minus the inverse of the propensity score (i.e., the propensity of NOT being in the treated group) in the controls.
When to use a balanced propensity score?
After creating a balanced propensity score, the next step is choosing how touse the propensity score to compare treatment and comparison groups. Thischoice involves evaluating tradeoffs between bias and efficiency. Matchingand weighting strategies are discussed here, as they are among the most popu-lar comparison strategies (Austin 2009b, 2011a).
How are weights calculated in a propensity score?
In weighting within strata, the weights are calculated based on the distribution of treated and control observations within each stratum. Like other propensity score methods, the data are split into strata based on propensity scores. Then a weight is assigned using the distribution of observations within the stratum.
Is the covariate adjustment of propensity score biased?
One popular method, covariate adjustment of the propensity score in a regression model, has been empirically shown to be biased in non-linear models. However, no compelling underlying theoretical reason has been presented.
How does matching by Propensity scores eliminate linearity?
Matching by propensity scores eliminates the linearity assumption, but, as some observations may not be matched, you may not be able to say anything about certain groups. For example, if you are studying a worker training program, you may have all the enrollees be men, but the control, non-participant population be composed of men and women.