Tests for detecting probability mass points

Byung Hill Jun; Hosin Song

doi:10.22841/KERDOI.2019.35.1.008

Tests for detecting probability mass points

Byung Hill Jun, Hosin Song

Department of Economics

Research output: Contribution to journal › Article › peer-review

Abstract

The objective of this paper is developing test statistics to detect the presence of mass points when data are possibly generated by a mixture of a continuous and a discrete distribution. To serve our purpose we propose two versions of the probability mass point (PMP) test. We derive the limiting distributions of the PMP test statistics under the null and alternative hypothesis by exploiting the asymptotic difference between two kernel density estimators with different bandwidths. Specifically, the proposed PMP test statistic is shown to converge to either the standard normal distribution or a linear transformation of a positive Poisson distribution at a non-mass point depending on bandwidths choice, while it diverges to infinity at a mass point. Numerical experiments are conducted to demonstrate the validity of our proposed tests. Korean taxpayers’ bunching behavior is considered as an empirical application.

Original language	English
Pages (from-to)	205-248
Number of pages	44
Journal	Korean Economic Review
Volume	35
Issue number	1
DOIs	https://doi.org/10.22841/KERDOI.2019.35.1.008
State	Published - 2019

Bibliographical note

Funding Information:
We are grateful for the helpful comments from two anonymous referees and seminar participants at the Asian Meeting of the Econometric Society, WEAI 89th Annual Conference, the 2016 China Meeting of the Econometric Society, the 2017 Autumn Meeting of JAAE, and the 2018 Annual Meeting of the Korean Econometric Society. This work was supported by the National Research Foundation of Korea Grant funded by the Korean Government (NRF-2014S1A5A8018660) and by the Hankuk University of Foreign Studies Research Fund.

Funding Information:
* We are grateful for the helpful comments from two anonymous referees and seminar participants at the Asian Meeting of the Econometric Society, WEAI 89th Annual Conference, the 2016 China Meeting of the Econometric Society, the 2017 Autumn Meeting of JAAE, and the 2018 Annual Meeting of the Korean Econometric Society. This work was supported by the National Research Foundation of Korea Grant funded by the Korean Government (NRF-2014S1A5A8018660) and by the Hankuk University of Foreign Studies Research Fund. ** First Author, Associate Professor, Department of International Economics and Law, Hankuk University of Foreign Studies, 107 Imun-ro, Dongdaemun-gu, Seoul, 02450, Korea. E-mail: [email protected]. *** Corresponding Author, Associate Professor, Department of Economics, Ewha Womans University, 52 Ewhayeodae-gil, Seodaemun-gu, Seoul, 03760, Korea. E-mail:[email protected].

Publisher Copyright:
© 2019, Korean Economic Association. All rights reserved.

Keywords

Bunching
Kernel Density Estimator
Probability Mass Point Test

Access to Document

10.22841/KERDOI.2019.35.1.008

Cite this

@article{356ad7d6f6d4466da99d1b5eed081b03,

title = "Tests for detecting probability mass points",

abstract = "The objective of this paper is developing test statistics to detect the presence of mass points when data are possibly generated by a mixture of a continuous and a discrete distribution. To serve our purpose we propose two versions of the probability mass point (PMP) test. We derive the limiting distributions of the PMP test statistics under the null and alternative hypothesis by exploiting the asymptotic difference between two kernel density estimators with different bandwidths. Specifically, the proposed PMP test statistic is shown to converge to either the standard normal distribution or a linear transformation of a positive Poisson distribution at a non-mass point depending on bandwidths choice, while it diverges to infinity at a mass point. Numerical experiments are conducted to demonstrate the validity of our proposed tests. Korean taxpayers{\textquoteright} bunching behavior is considered as an empirical application.",

keywords = "Bunching, Kernel Density Estimator, Probability Mass Point Test",

author = "Jun, {Byung Hill} and Hosin Song",

note = "Funding Information: We are grateful for the helpful comments from two anonymous referees and seminar participants at the Asian Meeting of the Econometric Society, WEAI 89th Annual Conference, the 2016 China Meeting of the Econometric Society, the 2017 Autumn Meeting of JAAE, and the 2018 Annual Meeting of the Korean Econometric Society. This work was supported by the National Research Foundation of Korea Grant funded by the Korean Government (NRF-2014S1A5A8018660) and by the Hankuk University of Foreign Studies Research Fund. Funding Information: * We are grateful for the helpful comments from two anonymous referees and seminar participants at the Asian Meeting of the Econometric Society, WEAI 89th Annual Conference, the 2016 China Meeting of the Econometric Society, the 2017 Autumn Meeting of JAAE, and the 2018 Annual Meeting of the Korean Econometric Society. This work was supported by the National Research Foundation of Korea Grant funded by the Korean Government (NRF-2014S1A5A8018660) and by the Hankuk University of Foreign Studies Research Fund. ** First Author, Associate Professor, Department of International Economics and Law, Hankuk University of Foreign Studies, 107 Imun-ro, Dongdaemun-gu, Seoul, 02450, Korea. E-mail: [email protected]. *** Corresponding Author, Associate Professor, Department of Economics, Ewha Womans University, 52 Ewhayeodae-gil, Seodaemun-gu, Seoul, 03760, Korea. E-mail:[email protected]. Publisher Copyright: {\textcopyright} 2019, Korean Economic Association. All rights reserved.",

year = "2019",

doi = "10.22841/KERDOI.2019.35.1.008",

language = "English",

volume = "35",

pages = "205--248",

journal = "Korean Economic Review",

issn = "0254-3737",

publisher = "The Korean Economic Association",

number = "1",

}

TY - JOUR

T1 - Tests for detecting probability mass points

AU - Jun, Byung Hill

AU - Song, Hosin

N1 - Funding Information: We are grateful for the helpful comments from two anonymous referees and seminar participants at the Asian Meeting of the Econometric Society, WEAI 89th Annual Conference, the 2016 China Meeting of the Econometric Society, the 2017 Autumn Meeting of JAAE, and the 2018 Annual Meeting of the Korean Econometric Society. This work was supported by the National Research Foundation of Korea Grant funded by the Korean Government (NRF-2014S1A5A8018660) and by the Hankuk University of Foreign Studies Research Fund. Funding Information: * We are grateful for the helpful comments from two anonymous referees and seminar participants at the Asian Meeting of the Econometric Society, WEAI 89th Annual Conference, the 2016 China Meeting of the Econometric Society, the 2017 Autumn Meeting of JAAE, and the 2018 Annual Meeting of the Korean Econometric Society. This work was supported by the National Research Foundation of Korea Grant funded by the Korean Government (NRF-2014S1A5A8018660) and by the Hankuk University of Foreign Studies Research Fund. ** First Author, Associate Professor, Department of International Economics and Law, Hankuk University of Foreign Studies, 107 Imun-ro, Dongdaemun-gu, Seoul, 02450, Korea. E-mail: [email protected]. *** Corresponding Author, Associate Professor, Department of Economics, Ewha Womans University, 52 Ewhayeodae-gil, Seodaemun-gu, Seoul, 03760, Korea. E-mail:[email protected]. Publisher Copyright: © 2019, Korean Economic Association. All rights reserved.

PY - 2019

Y1 - 2019

N2 - The objective of this paper is developing test statistics to detect the presence of mass points when data are possibly generated by a mixture of a continuous and a discrete distribution. To serve our purpose we propose two versions of the probability mass point (PMP) test. We derive the limiting distributions of the PMP test statistics under the null and alternative hypothesis by exploiting the asymptotic difference between two kernel density estimators with different bandwidths. Specifically, the proposed PMP test statistic is shown to converge to either the standard normal distribution or a linear transformation of a positive Poisson distribution at a non-mass point depending on bandwidths choice, while it diverges to infinity at a mass point. Numerical experiments are conducted to demonstrate the validity of our proposed tests. Korean taxpayers’ bunching behavior is considered as an empirical application.

AB - The objective of this paper is developing test statistics to detect the presence of mass points when data are possibly generated by a mixture of a continuous and a discrete distribution. To serve our purpose we propose two versions of the probability mass point (PMP) test. We derive the limiting distributions of the PMP test statistics under the null and alternative hypothesis by exploiting the asymptotic difference between two kernel density estimators with different bandwidths. Specifically, the proposed PMP test statistic is shown to converge to either the standard normal distribution or a linear transformation of a positive Poisson distribution at a non-mass point depending on bandwidths choice, while it diverges to infinity at a mass point. Numerical experiments are conducted to demonstrate the validity of our proposed tests. Korean taxpayers’ bunching behavior is considered as an empirical application.

KW - Bunching

KW - Kernel Density Estimator

KW - Probability Mass Point Test

UR - http://www.scopus.com/inward/record.url?scp=85115666890&partnerID=8YFLogxK

U2 - 10.22841/KERDOI.2019.35.1.008

DO - 10.22841/KERDOI.2019.35.1.008

M3 - Article

AN - SCOPUS:85115666890

SN - 0254-3737

VL - 35

SP - 205

EP - 248

JO - Korean Economic Review

JF - Korean Economic Review

IS - 1

ER -

Tests for detecting probability mass points

Abstract

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this