A data-driven procedure to determine the bunching window: an application to the Netherlands

Nicole Bosch,Vincent Dekker,Kristina Strohmaier

doi:10.1007/s10797-020-09590-w

Nicole Bosch, Vincent Dekker + Show 1 more

Open Access

https://doi.org/10.1007/s10797-020-09590-w

Copy DOI

Abstract

We extend the bunching approach introduced by Saez (Am Econ J Econ Policy 2:180–212, 2010) by proposing an intuitive, data-driven procedure to determine the bunching window. By choosing the bunching window ad hoc, researchers throw away informative data points for estimating the counterfactual income distribution in the absence of the kink. Assuming a descending bunching mass to both sides of the threshold, the proposed algorithm produces a distribution of lower and upper bounds for the bunching window. In each iteration, the bunching window is defined as all contiguous bin midpoints around the threshold that lie outside of the confidence band resulting from running a local regression through all data points outside of the excluded region. Monte Carlo simulations provide evidence that our data-driven procedure outperforms larger bunching windows in terms of bias and efficiency. In our application for the Netherlands, we find clear evidence of bunching behaviour at all three thresholds of the Dutch tax schedule with a precisely estimated elasticity of 0.023 at the upper threshold, which is driven by self-employed, women and joint tax filers.

Highlights

A central topic in public economics is the assessment of welfare losses caused by behavioural responses to income taxation
Following the seminal paper by Feldstein (1995), a large study emerged where welfare losses are inferred from the elasticity of taxable income (ETI)
Clear bunching behaviour can be seen at the first and third threshold, in line with the incentives set by the tax schedule

Summary

Introduction

A central topic in public economics is the assessment of welfare losses caused by behavioural responses to income taxation. Following the seminal paper by Feldstein (1995), a large study emerged where welfare losses are inferred from the elasticity of taxable income (ETI).. A growing strand of the literature utilises the bunching method to obtain a nonparametric estimate of the ETI (Saez 2010; Chetty et al 2011). This method exploits the clustering behaviour of individuals at kinks in a nonlinear tax system to identify the ETI by the number of individuals that adjust their income to stay below the threshold of a tax bracket. Using the bunching method is attractive as it builds on a sound theoretical foundation and is not susceptible to endogeneity biases, a problem suffered by the previous ETI literature (Saez 2010; Gruber and Saez 2002; Weber 2016).

Objectives

Results

Conclusion