Kirbom Araya Abay

PhD thesis by Kirbom Araya: "Essays on Microeconometric Modeling"

This thesis consists of three self-contained chapters, all dealing with micro-econometric modeling of road crash outcomes and all involving estimating simulation-based discrete choice models that accommodate unobserved heterogeneity and/or endogeneity effects. The first chapter investigates the injury severity of pedestrians considering alternative model specification and detailed road user behavior using a high-quality Danish road accident data. The alternative analytical specification of the models in this paper reveals that the choice of injury severity modeling approach has important implication on the empirical inferences associated with the effect of the explanatory variables in injury severity analysis. Particularly, the conventionally employed fixed-parameters standard ordered response injury severity model underestimates the marginal effects of some of the variables considered. The second chapter proposes a methodological  approach  that jointly models the injury severity of multiple individuals involved in a crash, while also recognizing the endogeneity of seat belt use in predicting injury severity levels as well as accommodating unobserved heterogeneity in the effects of variables. The analysis underscores the importance accommodating seat belt endogeneity effects and unobserved heterogeneity effects. The third chapter investigates the nature and impact of the reporting bias (sample selection) associated with the police-reported crash data on inferences made using this data. In doing so, we merge a detailed emergency room data and the commonly employed police-reported crash data for a specific region in Denmark. The empirical results in this paper confirm the existence of substantial reporting bias in the police-reported road crash data. This non-random sample selection associated with the police-reported crash data leads to biased estimates on the effect of some of the explanatory variables in injury severity analysis.