2022
DOI: 10.1016/j.jpubeco.2022.104679
|View full text |Cite
|
Sign up to set email alerts
|

The quality of the estimators of the ETI

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
5
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
8

Relationship

1
7

Authors

Journals

citations
Cited by 9 publications
(5 citation statements)
references
References 40 publications
0
5
0
Order By: Relevance
“…The results ofAronsson et al (2022) also show that IV regression estimators are typically imprecise, and that both IV estimators and polynomial bunching estimators are outperformed by an Indirect Inference estimator new to the ETI literature. 2 Saez (2010) and many subsequent studies rely on the same strict assumptions on individuals' preferences, as implied by the basic log-linear labor supply model, in order to identify the ETI.3 A model with heterogeneity in the ETI and the corresponding ML estimator are presented in a background working paper(Aronsson et al, 2021).…”
mentioning
confidence: 83%
See 1 more Smart Citation
“…The results ofAronsson et al (2022) also show that IV regression estimators are typically imprecise, and that both IV estimators and polynomial bunching estimators are outperformed by an Indirect Inference estimator new to the ETI literature. 2 Saez (2010) and many subsequent studies rely on the same strict assumptions on individuals' preferences, as implied by the basic log-linear labor supply model, in order to identify the ETI.3 A model with heterogeneity in the ETI and the corresponding ML estimator are presented in a background working paper(Aronsson et al, 2021).…”
mentioning
confidence: 83%
“…The literature largely relies on nonparametric methods such as polynomial smoothing based on histograms to calculate this counter-factual distribution (e.g., Chetty et al, 2011;Kleven & Waseem, 2013). In a Monte Carlo study, Aronsson et al (2022) show that the polynomial bunching estimator typically exhibits a downward bias, the size of which varies across settings and levels of the ETI. 1 More specifically, the polynomial approach is potentially problematic because (i) it relies on visual identification of the bunching range and (ii) the nonparametric estimate is based on the observed income density excluding the bunching range, which means that optimization errors are ignored outside this bunching interval.…”
Section: Introductionmentioning
confidence: 99%
“…12 See also Aronsson et al (2022a) for an overview and evaluation of different methods of estimating the elasticity of taxable income.…”
Section: Elasticities Of Taxable Incomementioning
confidence: 99%
“…Those countries that did not agree to mutual reporting agreed to an anonymous withholding tax on these capital incomes. 25 The treasury provides data on unsolicited declarations of previous evasion, see Finanzministerium des Landes Nordrhein-Westfalen, 2010, 2014 26 Estimates of the elasticity of taxable income (ETI) in general cover a wide range, primarily depending on the instrumentation of the net-of-tax rate (see for example Saez et al (2012), Weber (2014), Aronsson et al (2017), and Neisser (2021)). Doerrenberg et al (2017) show that the ETI in Germany seems to be primarily driven by deductions rather than real income generation: in their baseline specification, they find an ETI with respect to the net-of-tax rate Net income effect (% of pre-reform ENI) consider a range of different magnitudes of the elasticity of reported capital income in a back-ofthe-envelope calculation: Figure 3 shows the change of the NIE and NIE2 by income fractile if reported capital income reacts to its marginal net-of-tax rate with an elasticity between zero (corresponding to results in section 5) and one.…”
Section: Shifting Evasion and Real Responsesmentioning
confidence: 99%