Average Marginal Effects in One-Step Partially Linear Instrumental Regressions
TLDR
This paper introduces a novel RKHS-based method for estimating and inferring average marginal effects in partially linear instrumental regressions.
Key contributions
- Introduces a novel RKHS-based procedure for estimating average marginal effects in partially linear instrumental regressions.
- Achieves consistency and asymptotic normality for the proposed estimator with a single regularization parameter.
- Develops a valid Bayesian bootstrap method for inference, addressing the complex variance of the limiting distribution.
- Demonstrates strong finite-sample performance and practical utility through simulations and empirical applications.
Why it matters
This paper offers a robust and practical solution for estimating average marginal effects in complex econometric models. Its novel RKHS approach and valid Bayesian bootstrap inference simplify a challenging estimation problem, making it accessible for empirical research. The method's ease of implementation and strong performance are significant for applied econometrics.
Original Abstract
We propose a novel procedure for estimating and conducting inference on average marginal effects in partially linear instrumental regressions using Reproducing Kernel Hilbert Space methods. Our procedure relies on a single regularization parameter. We obtain the consistency and asymptotic normality of our estimator. Since the variance of the limiting distribution has a complex analytical form, we propose a Bayesian bootstrap method to conduct inference and establish its validity. Our procedure is easy to implement and exhibits good finite-sample performance in simulations. Three empirical applications illustrate its implementation on real data, showing that it yields economically meaningful results.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.