Please cite this article in press as: Gkritza, K., Mannering, F.L., Mixed logit analysis of safety-belt use in single- and multi-occupant vehicles, Accid. Anal. Prev. (2007), doi:10.1016/j.aap.2007.07.013 ARTICLE IN PRESS +Model AAP-1540; No. of Pages 9 Accident Analysis and Prevention xxx (2007) xxx–xxx Mixed logit analysis of safety-belt use in single- and multi-occupant vehicles Konstantina Gkritza a,1 , Fred L. Mannering b,∗ a Department of Civil, Construction & Environmental Engineering, 450 Town Engineering Building, Iowa State University, Ames, IA 50011-3232, United States b School of Civil Engineering, 550 Stadium Mall Drive, Purdue University, West Lafayette, IN 47907-2051, United States Received 13 June 2007; received in revised form 17 July 2007; accepted 20 July 2007 Abstract In this paper we demonstrate a modeling approach that can be used to better understand the use of safety belts in single- and multi-occupant vehicles, and the effect that vehicle, roadway and occupant characteristics have on usage rates. Using data from a roadside observational survey of safety-belt use in Indiana, a mixed (random parameters) logit model is estimated. Potentially interrelated choices of safety-belt use by drivers and front-seat passengers are examined. The approach we use also allows for the possibility that estimated model parameters can vary randomly across vehicle occupants to account for unobserved effects potentially relating to roadway characteristics, vehicle attributes, and driver behavior. Estimation findings indicate that the choices of safety-belt use involve a complex interaction of factors and that the effect of these factors can vary significantly across the population. Our results show that the mixed logit model can provide a much fuller understanding of the interaction of the numerous variables which correlate with safety-belt use than traditional discrete-outcome modeling approaches. © 2007 Elsevier Ltd. All rights reserved. Keywords: Mixed logit model; Random parameters; Safety-belt use; Passenger safety-belt use 1. Introduction In the United States, efforts to promote safety-belt use have been ongoing for several decades with mostly encour- aging results (see, for example National Highway Traffic Safety Administration, 1991; National Center for Statistics and Analysis, 2007). In 1984, New York became the first State to enact safety-belt use legislation and today, all States except New Hampshire have some form of a belt-use law that applies to motorists (at least the driver and front-seat occupants). Research that has focused on assessing the effectiveness of safety-belt laws for safety-belt use has concluded that safety-belt laws are one of the most effective approaches for increasing safety-belt use, and that primary belt-use laws (where vehicles can be stopped for non-compliant occupants) are more effective than secondary belt-use laws (where vehicles can only be stopped if another traffic infraction occurs) (Rivara et al., 1999; Dinh-Zarr et al., ∗ Corresponding author. Tel.: +1 765 496 7913. E-mail addresses: nadia@iasate.edu (K. Gkritza), flm@ecn.purdue.edu (F.L. Mannering). 1 Tel.: +1 515 867 7290. 2001; White and Washington, 2001; Wells et al., 2002; Cohen and Einav, 2003; Shults et al., 2004; Houston and Richardson, 2005). Still, as reported by Janssen (1994), Dee (1998) and Eluru and Bhat (in press), the effect of state safety-belt policies in terms of reducing injury severities might be more modest than that reported, because those most likely to be involved in severe traffic accidents (males, young drivers, or alcohol-users) have been significantly less responsive to safety-belt laws and their enforcement status (Shinar, 1993; Dee, 1998). Thus, with riskier drivers tending to be non-belted, comparisons of belted and non- belted injury severities may be overstating the effectiveness of safety belts because, had non-belted drivers been observed in accidents as belted, their injuries may be more severe because of their potentially more aggressive driving behavior relative to those normally observed to be belted. Aside from state safety-belt laws, several sociodemographic characteristics of motor vehicle occupants have been found to correlate with safety-belt use. In general, females have been found to be more likely to be observed wearing safety belts than males (see Preusser et al., 1991; Reinfurt et al., 1996; Nelson et al., 1998; Wells et al., 2002; Calisir and Lehto, 2002; Glassbrenner et al., 2004). Young adults have generally exhib- 0001-4575/$ – see front matter © 2007 Elsevier Ltd. All rights reserved. doi:10.1016/j.aap.2007.07.013