The empirical Bayes (EB) method addresses two problems of safety estimation: it increases the precision of estimates beyond what is possible when one is limited to the use of a 2- to 3-year accident history, and it corrects for the regression-to-mean bias. The increase in precision is important when the usual estimate is too imprecise to be useful. The elimination of the regression-to-mean bias is important whenever the accident history of the entity is in some way connected with the reason why its safety is estimated. The theory of the EB method is well developed. It is now used in the Interactive Highway Safety Design Model and will be used in the Comprehensive Highway Safety Improvement Model. The time has come for the EB method to be the standard and staple of professional practice. The study’s goal is to facilitate the transition from theory into practice.

Collisions between heavy trucks and passenger cars are a major concern because of the severity of injuries. This research has two objectives. One is to examine the impact of various factors on injuries to passenger car occupants involved in such collisions. Due to the complex interaction of factors influencing injury levels in truck-car collisions, the ordered probit model is used to identify specific variables significantly influencing levels of injury in two-vehicle rear-end involvements on divided roadways. Another objective is to demonstrate the use of the ordered probit in this complex highway safety problem. A set of vehicle, occupant, roadway, and environmental factors expected to influence injury severity was developed. Given two-vehicle passenger car-truck rear-end collisions, the variables that increase passenger vehicle occupant injury severity include darkness; high speed differentials; high speed limits; grades, especially when they are wet; being in a car struck to the rear (as opposed to being in a car striking a truck to the rear); driving while drunk; and being female. The interaction effects of cars being struck to the rear with high speed differentials and car rollovers were significant. Variables decreasing severity include snowy or icy roads, congested roads, being in a station wagon struck to the rear (as opposed to a sedan), and using a child restraint. With injuries ordered in five classes from no injury to fatalities, the marginal effects of each factor on the likelihood of each injury class are reported.Collisions between passenger cars and heavy trucks are of major concern to the traveling public and the trucking industry in the United States. This is largely due to the severity of injuries occurring in these events. The Insurance Institute for Highway Safety Fatality Facts 1996 edition reports that in 1995, tractor trailers had a higher fatal crash involvement rate [2.9 per 161 million km (100 million mi)] than passenger cars [1.9 per 161 million km (100 million mi)]. In 1995, though large trucks accounted for 3 percent of registered vehicles and 7 percent of vehicle kilometers (or miles) traveled, they were in crashes involving 12 percent of all motor vehicle deaths. Because of the importance of this problem and the complex nature of truckcar crashes, this study uses the ordered probit method for understanding the specific factors that influence injury severity in rear-end crashes involving these two vehicle types. This technique is particularly appropriate for analyzing ordinal categorical injury data, but has not been widely used in transportation safety.This paper seeks to understand how the personal attributes of passenger car occupants and drivers in combination with the vehicle, roadway, and environmental conditions influence the severity of an individual's injury in a rear-end collision involving a heavy truck. To test hypotheses empirically, the Federal Highway Administration's Highway Safety Information System (HSIS) database is used for

No abstract

Adverse weather can reduce visibility and road surface friction and thus increase crash frequency and injury severity. However, drivers may compensate for higher crash risk by reducing speeds, maintaining safe spacing, and driving more carefully. The impacts of adverse weather and its interactions with driver and roadway characteristics on the occurrence and injury severity of selected crash types are analyzed. Single-vehicle, two-vehicle sideswipe, and two-vehicle rear-end collisions on limited-access roadways are considered. To analyze differential impacts of adverse weather on crash type, binary probit models are estimated for single-vehicle versus the two types of two-vehicle crashes, and for rear-ends versus sideswipes. To analyze injury severity, ordered probit models are estimated. The 1990–1995 Highway Safety Information System (HSIS) database for North Carolina was used for analysis. The results indicate that, for the selected crash types, drivers appear to compensate for increased injury risks in that in adverse weather crashes are more frequent but injuries are less severe. Some implications for advanced weather systems are discussed.

The recent congressional action revoking the national maximum speed limits has rekindled the debate over safety and travel time tradeoff. The effect of speed limit increases on the most severe occupant injury in a crash is analyzed here. Single-vehicle crashes on Interstate highways in North Carolina ( N = 2729) are examined. Two analysis methods are used: a paired-comparison analysis and an ordered probit model. Increasing speed limits from 88.5 to 96.6 km/h (55 to 60 mph) and from 88.5 to 104.6 km/h (55 to 65 mph) increased the probability of sustaining minor and nonincapacitating injuries, but increasing speed limits from 104.6 to 112.7 km/h (65 to 70 mph) did not have a significant effect on crash severity. There were too few fatal crashes to draw conclusive results for this category of injury severity. Crashes involving the face of a guardrail were more severe on segments where the speed limit was raised than on comparison segments or study segments before the limits were increased. These findings may be conservative because study segments with good safety records were chosen for the speed limit increases.