A count data model with endogenous covariates: Formulation and application to roadway crash frequency at intersections

被引：60

作者：

Bhat, Chandra R. ^{[1
,2
]}

Born, Kathryn ^{[1
]}

Sidharthan, Raghuprasad ^{[3
]}

Bhat, Prerna C. ^{[4
]}

机构：

[1] Univ Texas Austin, Dept Civil Architectural & Environm Engn, 301 E Dean Keeton St,Stop C1761, Austin, TX 78712 USA

[2] King Abdulaziz Univ, Jeddah 21589, Saudi Arabia

[3] Parsons Brinckerhoff, Seattle, WA 8104 USA

[4] Harvard Univ, Cambridge, MA 02138 USA

来源：

ANALYTIC METHODS IN ACCIDENT RESEARCH | 2014年 / 1卷

关键词：

Count data; Treatment-outcome models; Accident analysis; Generalized ordered response; Flashing light control;

D O I：

10.1016/j.amar.2013.10.001

中图分类号：

R1 [预防医学、卫生学];

学科分类号：

1004 ; 120402 ;

摘要：

This paper proposes an estimation approach for count data models with endogenous covariates. The maximum approximate composite marginal likelihood inference approach is used to estimate model parameters. The modeling framework is applied to predict crash frequency at urban intersections in Irving, Texas. The sample is drawn from the Texas Department. of Transportation (TxDOT) crash incident files for the year 2008. The results highlight the importance of accommodating endogeneity areas in count. models. in addition, the results reveal the increased propensity for crashes at intersections with flashing lighrs, intersections with crest. approaches, and intersections that are on frontage roads. (C) 2013 Elsevier Ltd. All rights reserved.

引用

页码：53 / 71

页数：19

共 40 条

[1]

Abdel-Aty M, 2006, TRANSPORT RES REC, P98

[2] A note on modeling vehicle accident frequencies with random-parameters count models [J].

Anastasopoulos, Panagiotis Ch. ;

Mannering, Fred .

ACCIDENT ANALYSIS AND PREVENTION, 2009, 41 (01) :153-159

[3]

BARBARESSO JC, 1987, ITE J, V57, P41

[4]

Beck L. F., 2011, Morbidity and Mortality Weekly Report, V59, P1681

[5] The maximum approximate composite marginal likelihood (MACML) estimation of multinomial probit-based unordered response choice models [J].

Bhat, Chandra R. .

TRANSPORTATION RESEARCH PART B-METHODOLOGICAL, 2011, 45 (07) :923-939

[6] A copula-based approach to accommodate residential self-selection effects in travel behavior modeling [J].

Bhat, Chandra R. ;

Eluru, Naveen .

TRANSPORTATION RESEARCH PART B-METHODOLOGICAL, 2009, 43 (07) :749-765

[7] Accommodating flexible substitution patterns in multi-dimensional choice modeling: Formulation and application to travel mode and departure time choice [J].

Bhat, CR .

TRANSPORTATION RESEARCH PART B-METHODOLOGICAL, 1998, 32 (07) :455-466

[8] A spatial generalized ordered response model to examine highway crash injury severity [J].

Castro, Marisol ;

Paleti, Rajesh ;

Bhat, Chandra R. .

ACCIDENT ANALYSIS AND PREVENTION, 2013, 52 :188-203

[9] A latent variable representation of count data models to accommodate spatial and temporal dependence: Application to predicting crash frequency at intersections [J].

Castro, Marisol ;

Paleti, Rajesh ;

Bhat, Chandra R. .

TRANSPORTATION RESEARCH PART B-METHODOLOGICAL, 2012, 46 (01) :253-272

[10] ANALYSIS OF COVARIANCE WITH QUALITATIVE DATA [J].

CHAMBERLAIN, G .

REVIEW OF ECONOMIC STUDIES, 1980, 47 (01) :225-238

← 1 2 3 4 →