Propensity Score Matching for Multiple Treatments using Generalized Boosted Models: Code
The document includes the codes for propensity score analysis based on multiple treatments, as well as the matching results for a dataset on R&D subsidies among Chinese high-tech manufacturing firms in Jiangsu Province. In the dataset, firms can receive a national subsidy or a provincial subsidy, which have different selection criteria. Propensity score analysis becomes complicated when there are multiple treatments. Existing studies bypass this complication by focusing on two of the treatments at a time and calculate the pairwise treatment effects, but this pairwise comparison does not allow advanced analysis that investigates how different treatments interact with other variables to influence the dependent variable. Our code illustrates how to obtain a matched sample with balanced pretreatment variables for a dataset with multiple treatments. Using Generalized Boosted Models (GBMs) to calculate the generalized propensity score vector, our proposed procedure matches observations on a multi-dimensional space. After obtaining the matched sample, researchers can directly conduct complex econometric analysis using standard statistical packages without the necessity of additional programming. Our results also demonstrate the advantage of GBMs over the commonly-used multinomial logistic regressions in calculating the generalized propensity score.