Description

Random forests are a powerful tool of nonparametric data science and have been studied intensively for their theoretical properties and applicability in many scientific fields. Among the newest insights into their asymptotics are extensions towards Generalized Random Forests (GRF) with a central limit theorem allowing to study the pointwise influence of features/variables identified as the solution to various forms of local moment equations. Here, we extend these findings in Athey et al. (2019) towards uniformity, hence allowing to check whether over a range of feature values one observes significant effects. A feasible multiplier bootstrap procedure is developed to determine the critical values for the uniform confidence bands. Numerical simulations justify that this 'wild bootstrap' type method gives reliable coverage for inference, also in small samples. As a real data illustration, we revisit the mother's labor force application based on the sample used in Athey et al. (2019) and find that the father's low income doesn't always drive the causal effect of having a third child on women's labor force participation. All numerical codes and data can be found on https://quantlet.com/quantlet.com.