Errors-in-variables jump regression using local clustering

Yicheng Kang, Xiaodong Gong, Jiti Gao, Peihua Qiu

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Errors-in-variables (EIV) regression is widely used in econometric models. The statistical analysis becomes challenging when the regression function is discontinuous and the distribution of measurement error is unknown. In the literature, most existing jump regression methods either assume that there is no measurement error involved or require that jumps are explicitly detected before the regression function can be estimated. In some applications, however, the ultimate goal is to estimate the regression function and to preserve the jumps in the process of estimation. In this paper, we are concerned with reconstructing jump regression curve from data that involve measurement error. We propose a direct jump-preserving method that does not explicitly detect jumps. The challenge of restoring jump structure masked by measurement error is handled by local clustering. Theoretical analysis shows that the proposed curve estimator is statistically consistent. A numerical comparison with an existing jump regression method highlights its jump-preserving property. Finally, we demonstrate our method by an application to a health tax policy study in Australia.

Original languageEnglish
Pages (from-to)3642-3655
Number of pages14
JournalStatistics in Medicine
Volume38
Issue number19
DOIs
Publication statusPublished - Aug 2019

Keywords

  • clustering
  • discontinuities
  • health care
  • kernel smoothing
  • local regression
  • measurement errors
  • price elasticity

Cite this

Kang, Yicheng ; Gong, Xiaodong ; Gao, Jiti ; Qiu, Peihua. / Errors-in-variables jump regression using local clustering. In: Statistics in Medicine. 2019 ; Vol. 38, No. 19. pp. 3642-3655.
@article{a8d12f70e7c441e99cbd547b92e09420,
title = "Errors-in-variables jump regression using local clustering",
abstract = "Errors-in-variables (EIV) regression is widely used in econometric models. The statistical analysis becomes challenging when the regression function is discontinuous and the distribution of measurement error is unknown. In the literature, most existing jump regression methods either assume that there is no measurement error involved or require that jumps are explicitly detected before the regression function can be estimated. In some applications, however, the ultimate goal is to estimate the regression function and to preserve the jumps in the process of estimation. In this paper, we are concerned with reconstructing jump regression curve from data that involve measurement error. We propose a direct jump-preserving method that does not explicitly detect jumps. The challenge of restoring jump structure masked by measurement error is handled by local clustering. Theoretical analysis shows that the proposed curve estimator is statistically consistent. A numerical comparison with an existing jump regression method highlights its jump-preserving property. Finally, we demonstrate our method by an application to a health tax policy study in Australia.",
keywords = "clustering, discontinuities, health care, kernel smoothing, local regression, measurement errors, price elasticity",
author = "Yicheng Kang and Xiaodong Gong and Jiti Gao and Peihua Qiu",
year = "2019",
month = "8",
doi = "10.1002/sim.8205",
language = "English",
volume = "38",
pages = "3642--3655",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley & Sons",
number = "19",

}

Errors-in-variables jump regression using local clustering. / Kang, Yicheng; Gong, Xiaodong; Gao, Jiti; Qiu, Peihua.

In: Statistics in Medicine, Vol. 38, No. 19, 08.2019, p. 3642-3655.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Errors-in-variables jump regression using local clustering

AU - Kang, Yicheng

AU - Gong, Xiaodong

AU - Gao, Jiti

AU - Qiu, Peihua

PY - 2019/8

Y1 - 2019/8

N2 - Errors-in-variables (EIV) regression is widely used in econometric models. The statistical analysis becomes challenging when the regression function is discontinuous and the distribution of measurement error is unknown. In the literature, most existing jump regression methods either assume that there is no measurement error involved or require that jumps are explicitly detected before the regression function can be estimated. In some applications, however, the ultimate goal is to estimate the regression function and to preserve the jumps in the process of estimation. In this paper, we are concerned with reconstructing jump regression curve from data that involve measurement error. We propose a direct jump-preserving method that does not explicitly detect jumps. The challenge of restoring jump structure masked by measurement error is handled by local clustering. Theoretical analysis shows that the proposed curve estimator is statistically consistent. A numerical comparison with an existing jump regression method highlights its jump-preserving property. Finally, we demonstrate our method by an application to a health tax policy study in Australia.

AB - Errors-in-variables (EIV) regression is widely used in econometric models. The statistical analysis becomes challenging when the regression function is discontinuous and the distribution of measurement error is unknown. In the literature, most existing jump regression methods either assume that there is no measurement error involved or require that jumps are explicitly detected before the regression function can be estimated. In some applications, however, the ultimate goal is to estimate the regression function and to preserve the jumps in the process of estimation. In this paper, we are concerned with reconstructing jump regression curve from data that involve measurement error. We propose a direct jump-preserving method that does not explicitly detect jumps. The challenge of restoring jump structure masked by measurement error is handled by local clustering. Theoretical analysis shows that the proposed curve estimator is statistically consistent. A numerical comparison with an existing jump regression method highlights its jump-preserving property. Finally, we demonstrate our method by an application to a health tax policy study in Australia.

KW - clustering

KW - discontinuities

KW - health care

KW - kernel smoothing

KW - local regression

KW - measurement errors

KW - price elasticity

UR - http://www.scopus.com/inward/record.url?scp=85066911005&partnerID=8YFLogxK

U2 - 10.1002/sim.8205

DO - 10.1002/sim.8205

M3 - Article

VL - 38

SP - 3642

EP - 3655

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 19

ER -