Abstract:
|
Much evidence in health policy research is based on observational studies. Researchers who conduct observational studies typically assume that there are no unobservable differences between the treatment groups under comparison. Treatment effectiveness is estimated after adjusting for observed differences between comparison groups. There has been an explosion in the number of methods that can be used to adjust for observed confounders. While regression models were long the lone option, investigators can choose between many forms of matching, weighting, doubly robust, and machine learning methods. The choice of method is directly related to the possibility that estimates may be biased due to misspecification of the statistical model. That is, if the method of treatment effect estimation imposes unduly strong functional form assumptions, treatment effect estimates may be inaccurate leading to inappropriate recommendations about policy decisions. In this roundtable, we will conduct a comprehensive discussion of the methods available to investigators. We will outline advantages and disadvantages of the various methods, and we will discuss best practice for use in health policy research.
|