Practical Kolmogorov–Smirnov Testing by Minimum Distance Applied to Measure Top Income Shares in Korea

Jin Seo Cho, Myung Ho Park, Peter C.B. Phillips

Research output: Contribution to journalArticle

Abstract

We study Kolmogorov–Smirnov goodness-of-fit tests for evaluating distributional hypotheses where unknown parameters need to be fitted. Following the work of Pollard (1980), our approach uses a Cramér–von Mises minimum distance estimator for parameter estimation. The asymptotic null distribution of the resulting test statistic is represented by invariance principle arguments as a functional of a Brownian bridge in a simple regression format for which asymptotic critical values are readily delivered by simulations. Asymptotic power is examined under fixed and local alternatives and finite sample performance of the test is evaluated in simulations. The test is applied to measure top income shares using Korean income tax return data over 2007–2012. When the data relate to estimating the upper 0.1% or higher income shares, the conventional assumption of a Pareto tail distribution cannot be rejected. But the Pareto tail hypothesis is rejected for estimating the top 1.0% or 0.5% income shares at the 5% significance level. A supplement containing proofs and data descriptions is available online.

Original languageEnglish
Pages (from-to)523-537
Number of pages15
JournalJournal of Business and Economic Statistics
Volume36
Issue number3
DOIs
Publication statusPublished - 2018 Jul 3

Fingerprint

Minimum Distance
Korea
Pareto
income
Testing
Tail
Minimum Distance Estimator
Brownian Bridge
Asymptotic Power
Local Alternatives
Invariance Principle
Significance level
Null Distribution
Tax
Goodness of Fit Test
Unknown Parameters
Asymptotic distribution
simulation
Test Statistic
Critical value

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Social Sciences (miscellaneous)
  • Economics and Econometrics
  • Statistics, Probability and Uncertainty

Cite this

@article{8adea305052a4e418ec42b8d33bd0d43,
title = "Practical Kolmogorov–Smirnov Testing by Minimum Distance Applied to Measure Top Income Shares in Korea",
abstract = "We study Kolmogorov–Smirnov goodness-of-fit tests for evaluating distributional hypotheses where unknown parameters need to be fitted. Following the work of Pollard (1980), our approach uses a Cram{\'e}r–von Mises minimum distance estimator for parameter estimation. The asymptotic null distribution of the resulting test statistic is represented by invariance principle arguments as a functional of a Brownian bridge in a simple regression format for which asymptotic critical values are readily delivered by simulations. Asymptotic power is examined under fixed and local alternatives and finite sample performance of the test is evaluated in simulations. The test is applied to measure top income shares using Korean income tax return data over 2007–2012. When the data relate to estimating the upper 0.1{\%} or higher income shares, the conventional assumption of a Pareto tail distribution cannot be rejected. But the Pareto tail hypothesis is rejected for estimating the top 1.0{\%} or 0.5{\%} income shares at the 5{\%} significance level. A supplement containing proofs and data descriptions is available online.",
author = "Cho, {Jin Seo} and Park, {Myung Ho} and Phillips, {Peter C.B.}",
year = "2018",
month = "7",
day = "3",
doi = "10.1080/07350015.2016.1200983",
language = "English",
volume = "36",
pages = "523--537",
journal = "Journal of Business and Economic Statistics",
issn = "0735-0015",
publisher = "American Statistical Association",
number = "3",

}

Practical Kolmogorov–Smirnov Testing by Minimum Distance Applied to Measure Top Income Shares in Korea. / Cho, Jin Seo; Park, Myung Ho; Phillips, Peter C.B.

In: Journal of Business and Economic Statistics, Vol. 36, No. 3, 03.07.2018, p. 523-537.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Practical Kolmogorov–Smirnov Testing by Minimum Distance Applied to Measure Top Income Shares in Korea

AU - Cho, Jin Seo

AU - Park, Myung Ho

AU - Phillips, Peter C.B.

PY - 2018/7/3

Y1 - 2018/7/3

N2 - We study Kolmogorov–Smirnov goodness-of-fit tests for evaluating distributional hypotheses where unknown parameters need to be fitted. Following the work of Pollard (1980), our approach uses a Cramér–von Mises minimum distance estimator for parameter estimation. The asymptotic null distribution of the resulting test statistic is represented by invariance principle arguments as a functional of a Brownian bridge in a simple regression format for which asymptotic critical values are readily delivered by simulations. Asymptotic power is examined under fixed and local alternatives and finite sample performance of the test is evaluated in simulations. The test is applied to measure top income shares using Korean income tax return data over 2007–2012. When the data relate to estimating the upper 0.1% or higher income shares, the conventional assumption of a Pareto tail distribution cannot be rejected. But the Pareto tail hypothesis is rejected for estimating the top 1.0% or 0.5% income shares at the 5% significance level. A supplement containing proofs and data descriptions is available online.

AB - We study Kolmogorov–Smirnov goodness-of-fit tests for evaluating distributional hypotheses where unknown parameters need to be fitted. Following the work of Pollard (1980), our approach uses a Cramér–von Mises minimum distance estimator for parameter estimation. The asymptotic null distribution of the resulting test statistic is represented by invariance principle arguments as a functional of a Brownian bridge in a simple regression format for which asymptotic critical values are readily delivered by simulations. Asymptotic power is examined under fixed and local alternatives and finite sample performance of the test is evaluated in simulations. The test is applied to measure top income shares using Korean income tax return data over 2007–2012. When the data relate to estimating the upper 0.1% or higher income shares, the conventional assumption of a Pareto tail distribution cannot be rejected. But the Pareto tail hypothesis is rejected for estimating the top 1.0% or 0.5% income shares at the 5% significance level. A supplement containing proofs and data descriptions is available online.

UR - http://www.scopus.com/inward/record.url?scp=85019139969&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019139969&partnerID=8YFLogxK

U2 - 10.1080/07350015.2016.1200983

DO - 10.1080/07350015.2016.1200983

M3 - Article

VL - 36

SP - 523

EP - 537

JO - Journal of Business and Economic Statistics

JF - Journal of Business and Economic Statistics

SN - 0735-0015

IS - 3

ER -