Composite likelihood estimation in multivariate data analysis

Transportation Research Part B: Methodological

2013

126

In loving memory of my grandmother N. N. Rugmani AcknowledgmentsFirst and foremost, I must express appreciation to Dr. Chandra Bhat, with whom it has been a pleasure and a privilege to work. I thank him for his insights and advice as also for the stimulus and motivation to dig deep into research. I am grateful to him for showing me how to make sense of mathematical models and for instilling in me the notion that writing should be simple, direct, logical, and tight. His invaluable ideas and the high standards that he sets for himself and his students form the backbone of

Section: Model Estimationmentioning

confidence: 99%

On accommodating spatial dependence in bicycle and pedestrian injury counts by severity level

Narayanamoorthy

Transportation Research Part B: Methodological

2013

126

“…Under usual regularity assumptions (Molenberghs andVerbeke, 2005, Xu and, the CML estimator of θ is consistent and asymptotically normal distributed with asymptotic mean θ and covariance matrix given by the inverse of Godambe's (1960) sandwich information matrix ) (θ G (see Zhao and Joe, 2005):…”

Section: Model Estimationmentioning

confidence: 99%

A spatial generalized ordered response model to examine highway crash injury severity

Castro

Accident Analysis & Prevention

2013

108

This paper proposes a flexible econometric structure for injury severity analysis at the level of individual crashes that recognizes the ordinal nature of injury severity categories, allows unobserved heterogeneity in the effects of contributing factors, as well as accommodates spatial dependencies in the injury severity levels experienced in crashes that occur close to one another in space. The modeling framework is applied to analyze the injury severity sustained in crashes occurring on highway road segments in Austin, Texas. The sample is drawn from the Texas Department of Transportation (TxDOT) crash incident files from 2009 and includes a variety of crash characteristics, highway design attributes, driver and vehicle characteristics, and environmental factors. The results from our analysis underscore the value of our proposed model for data fit purposes as well as to accurately estimate variable effects. The most important determinants of injury severity on highways, according to our results, are (1) whether any vehicle occupant is ejected, (2) whether collision type is head-on, (3) whether any vehicle involved in the crash overturned, (4) whether any vehicle occupant is unrestrained by a seat-belt, and (5) whether a commercial truck is involved.

“…The properties of the general CML estimator may be derived using the theory of estimating equations (see Cox andReid, 2004, Yi et al, 2011). Specifically, under usual regularity assumptions (Molenberghs andVerbeke, 2005, page 191, Xu and, the CML estimator of θ is consistent and asymptotically normal distributed with asymptotic mean θ and covariance matrix given by the inverse of Godambe's (1960) sandwich information matrix (see Zhao and Joe, 2005):…”

Section: The Composite Marginal Likelihood Approachmentioning

confidence: 99%

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

Castro

Transportation Research Part B: Methodological

2012

135

This paper proposes a reformulation of count models as a special case of generalized orderedresponse models in which a single latent continuous variable is partitioned into mutually exclusive intervals. Using this equivalent latent variable-based generalized ordered response framework for count data models, we are then able to gainfully and efficiently introduce temporal and spatial dependencies through the latent continuous variables. Our formulation also allows handling excess zeros in correlated count data, a phenomenon that is commonly found in