Estimation and Inference for Moments of Ratios with Robustness against Large Trimming Bias

Abstract

Empirical researchers often trim observations with small denominator A when they estimate moments of the form E[B/A]. Large trimming is a common practice to mitigate variance, but it incurs large trimming bias. This paper provides a novel method of correcting large trimming bias. If a researcher is willing to assume that the joint distribution between A and B is smooth, then a large trimming bias may be estimated well. With the bias correction, we also develop a valid and robust inference result for E[B/A].

References in corpus (1)

• Optimal Uniform Convergence Rates and Asymptotic Normality for Series Estimators Under Weak Dependence and Weak Conditions

Cited by in corpus (3)

• Robust Inference Using Inverse Probability Weighting
• Biased-sample empirical likelihood weighting: an alternative to inverse probability weighting
• Slow Movers in Panel Data