On Binscatter

TL;DR

This paper provides a formal analysis of binscatter, introduces improved visualization and econometric tools, addresses a covariate adjustment issue, and demonstrates the impact of these enhancements on real applications.

Contribution

It develops optimal binning and uncertainty quantification methods for binscatter, and highlights a covariate adjustment problem affecting conclusions.

Findings

Enhanced visualization and econometric tools for binscatter

Identification of a covariate adjustment problem

Revised results in two empirical applications

Abstract

Binscatter is a popular method for visualizing bivariate relationships and conducting informal specification testing. We study the properties of this method formally and develop enhanced visualization and econometric binscatter tools. These include estimating conditional means with optimal binning and quantifying uncertainty. We also highlight a methodological problem related to covariate adjustment that can yield incorrect conclusions. We revisit two applications using our methodology and find substantially different results relative to those obtained using prior informal binscatter methods. General purpose software in Python, R, and Stata is provided. Our technical work is of independent interest for the nonparametric partition-based estimation literature.