SEMIPARAMETRIC ESTIMATION of CENSORED SPATIAL AUTOREGRESSIVE MODELS

Tadao Hoshino

doi:10.1017/S0266466618000488

SEMIPARAMETRIC ESTIMATION of CENSORED SPATIAL AUTOREGRESSIVE MODELS

Tadao Hoshino

School of Political Science and Economics

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

Abstract

This study considers the estimation of spatial autoregressive models with censored dependent variables, where the spatial autocorrelation exists within the uncensored latent dependent variables. The estimator proposed in this paper is semiparametric, in the sense that the error distribution is not parametrically specified and can be heteroskedastic. Under a median restriction, we show that the proposed estimator is consistent and asymptotically normally distributed. As an empirical illustration, we investigate the determinants of the risk of assault and other violent crimes including injury in the Tokyo metropolitan area.

Original language	English
Pages (from-to)	48-85
Number of pages	38
Journal	Econometric Theory
Volume	36
Issue number	1
DOIs	https://doi.org/10.1017/S0266466618000488
Publication status	Published - 2020 Feb 1

ASJC Scopus subject areas

Social Sciences (miscellaneous)
Economics and Econometrics

Access to Document

10.1017/S0266466618000488

Fingerprint Dive into the research topics of 'SEMIPARAMETRIC ESTIMATION of CENSORED SPATIAL AUTOREGRESSIVE MODELS'. Together they form a unique fingerprint.

Cite this

@article{5f3fbc16b86f4fd68f4c47783b0c914a,

title = "SEMIPARAMETRIC ESTIMATION of CENSORED SPATIAL AUTOREGRESSIVE MODELS",

abstract = "This study considers the estimation of spatial autoregressive models with censored dependent variables, where the spatial autocorrelation exists within the uncensored latent dependent variables. The estimator proposed in this paper is semiparametric, in the sense that the error distribution is not parametrically specified and can be heteroskedastic. Under a median restriction, we show that the proposed estimator is consistent and asymptotically normally distributed. As an empirical illustration, we investigate the determinants of the risk of assault and other violent crimes including injury in the Tokyo metropolitan area.",

author = "Tadao Hoshino",

note = "Funding Information: I thank Mamoru Amemiya for allowing me to use his data set, and the participants of the ESEM 2016 and the CUHK econometrics seminar 2017 for valuable suggestions. This work was supported financially by JSPS Grant-in-Aid for Young Scientists B-15K17039. Funding Information: I thank Mamoru Amemiya for allowing me to use his data set, and the participants of the ESEM 2016 and the CUHK econometrics seminar 2017 for valuable suggestions. This work was supported financially by JSPS Grant-in-Aid for Young Scientists B-15K17039. Address correspondence to Tadao Hoshino, School of Political Science and Economics, Waseda University, 1-6-1 Nishi-waseda, Shinjuku-ku, Tokyo 169-8050, Japan; e-mail: thoshino@waseda.jp.",

year = "2020",

month = feb,

day = "1",

doi = "10.1017/S0266466618000488",

language = "English",

volume = "36",

pages = "48--85",

journal = "Econometric Theory",

issn = "0266-4666",

publisher = "Cambridge University Press",

number = "1",

}

TY - JOUR

T1 - SEMIPARAMETRIC ESTIMATION of CENSORED SPATIAL AUTOREGRESSIVE MODELS

AU - Hoshino, Tadao

N1 - Funding Information: I thank Mamoru Amemiya for allowing me to use his data set, and the participants of the ESEM 2016 and the CUHK econometrics seminar 2017 for valuable suggestions. This work was supported financially by JSPS Grant-in-Aid for Young Scientists B-15K17039. Funding Information: I thank Mamoru Amemiya for allowing me to use his data set, and the participants of the ESEM 2016 and the CUHK econometrics seminar 2017 for valuable suggestions. This work was supported financially by JSPS Grant-in-Aid for Young Scientists B-15K17039. Address correspondence to Tadao Hoshino, School of Political Science and Economics, Waseda University, 1-6-1 Nishi-waseda, Shinjuku-ku, Tokyo 169-8050, Japan; e-mail: thoshino@waseda.jp.

PY - 2020/2/1

Y1 - 2020/2/1

N2 - This study considers the estimation of spatial autoregressive models with censored dependent variables, where the spatial autocorrelation exists within the uncensored latent dependent variables. The estimator proposed in this paper is semiparametric, in the sense that the error distribution is not parametrically specified and can be heteroskedastic. Under a median restriction, we show that the proposed estimator is consistent and asymptotically normally distributed. As an empirical illustration, we investigate the determinants of the risk of assault and other violent crimes including injury in the Tokyo metropolitan area.

AB - This study considers the estimation of spatial autoregressive models with censored dependent variables, where the spatial autocorrelation exists within the uncensored latent dependent variables. The estimator proposed in this paper is semiparametric, in the sense that the error distribution is not parametrically specified and can be heteroskedastic. Under a median restriction, we show that the proposed estimator is consistent and asymptotically normally distributed. As an empirical illustration, we investigate the determinants of the risk of assault and other violent crimes including injury in the Tokyo metropolitan area.

UR - http://www.scopus.com/inward/record.url?scp=85078456603&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85078456603&partnerID=8YFLogxK

U2 - 10.1017/S0266466618000488

DO - 10.1017/S0266466618000488

M3 - Article

AN - SCOPUS:85078456603

VL - 36

SP - 48

EP - 85

JO - Econometric Theory

JF - Econometric Theory

SN - 0266-4666

IS - 1

ER -

SEMIPARAMETRIC ESTIMATION of CENSORED SPATIAL AUTOREGRESSIVE MODELS

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Cite this