Michael Pawlovich

The choice of statistical models in road safety countermeasure effectiveness studies in Iowa

With few exceptions, model selection in traffic safety studies does not receive as much attention as do the methods implemented to estimate the parameters in those models. In this manuscript, we focus on the modeling step in an intervention study and discuss issues associated with formulation, interpretation, comparison and selection of models for intervention studies. All of the statistical models we consider rely on an over-dispersed Poisson assumption for the crash densities, and are fitted by Bayesian methods. The crash data we use arose from a study by the Iowa Department of Transportation to evaluate the effectiveness of converting roads from four lanes to three lanes. Deviance and the deviance information criterion (DIC) are used for model selection. In the Iowa road diet study, a subset of best models (which fit the data better than others) was then also used to carry out posterior predictive checks to assess model fit.

Iowa's experience with road diet measures : Use of bayesian approach to assess impacts on crash frequencies and crash rates

A before-and-after study implemented from a Bayesian perspective to assess crash history reduction due to road diets in Iowa was conducted by the Iowa State University Department of Statistics in cooperation with the Iowa Department of Transportations Office of Traffic and Safety. The study used both monthly crash data and estimated volumes obtained from TAS for 30 sites—15 treatment and 15 comparison-over 23 years (1982 to 2004). The sites had volumes ranging from 2,030 to 15, 350 during this period and were largely located in smaller urbanized areas. The research objective was to assess whether road diets appear to result in crash reductions on Iowa roads. Crash data were analyzed at each site before and after the conversions were completed. Given the random, rare nature of crash events, a hierarchical Poisson model was fitted, such that log mean rate was expressed as a piecewise linear function of time period, seasonal effects, and a random effect corresponding to each site. Monthly traffic volumes we...

Teenage driver crash incidence and factors influencing crash injury by rurality.

BACKGROUND Previous research has identified teenage drivers as having an increased risk for motor-vehicle crash injury compared with older drivers, and rural roads as having increased crash severity compared with urban roads. Few studies have examined incidence and characteristics of teen driver-involved crashes on rural and urban roads. METHODS All crashes involving a driver aged 10 through 18 were identified from the Iowa Department of Transportation crash data from 2002 through 2008. Rates of overall crashes and fatal or severe injury crashes were calculated for urban, suburban, rural, and remote rural areas. The distribution of driver and crash characteristics were compared between rural and urban crashes. Logistic regression was used to identify driver and crash characteristics associated with increased odds of fatal or severe injury among urban and rural crashes. RESULTS For younger teen drivers (age 10 through 15), overall crash rates were higher for more rural areas, although for older teen drivers (age 16 through 18) the overall crash rates were lower for rural areas. Rural teen crashes were nearly five times more likely to lead to a fatal or severe injury crash than urban teen crashes. Rural crashes were more likely to involve single vehicles, be late at night, involve a failure to yield the right-of-way and crossing the center divider. CONCLUSIONS Intervention programs to increase safe teen driving in rural areas need to address specific risk factors associated with rural roadways. IMPACT ON INDUSTRY Teen crashes cause lost work time for teen workers as well as their parents. Industries such as safety, health care, and insurance have a vested interest in enhanced vehicle safety, and these efforts should address risks and injury differentials in urban and rural roadways.

Evaluation of Iowa's graduated driver's licensing program

The effectiveness of Iowas graduated drivers licensing (GDL) program was evaluated for a 4-year period before and after implementation in 1999. Since some changes had occurred in the crash reporting format, changes in crash rates for younger drivers were compared to those for 35-44-year-old drivers (middle-age group of drivers) who were used as a control group. After implementation of GDL, the 14-, 16- and 17-year-old age groups experienced a greater decrease in crash rate than the middle-age control group while 15-year-old experienced a smaller decrease. This suggests that the crash rate for 15-year-old drivers may actually have increased when downward trends were adjusted for. Iowas GDL program allows holders of the instruction permit to travel unaccompanied to and from school and school-endorsed activities after obtaining a minor school license. Fifteen-year-old with minor school licenses account for up to 26.7% of 15-year-old license holders yet represent up to 74.8% of 15-year-old drivers involved in crashes (depending on the year) from 1998 to 2004. As a result, 15-year-old drivers with minor school licenses are involved in 7.2-8.9 times more crashes, are 7.7 times more likely to have one or more sanctions, and are 4.8 times more likely to receive one or more moving convictions than their peers with a regular instruction permit. This help may explain why 15-year-old drivers did not seem to benefit from implementation of the GDL program in Iowa.

Safety Evaluation of Destination Lighting Treatment at Stop Controlled Cross-Intersections

Intersection crashes during nighttime hours may occur because of poor driver visual cognition of conflicting traffic or intersection presence. In rural areas, the only source of lighting is typically provided by vehicle headlights. Roadway lighting enhances driver recognition of intersection presence and visibility of signs and markings. Destination lighting provides some illumination for the intersection but is not intended to fully illuminate all approaches. Destination lighting has been widely used in Iowa but the effectiveness has not been well documented. This study, therefore, sought to evaluate the effect on safety of destination lighting at rural intersections. As part of an extensive data collection effort, locations with destination/street lighting were gathered with the assistance of several state agencies. After manual selection of a similar number of control intersections, propensity score matching using the caliper width technique was used to match 245 treatments with 245 control sites. Negative binomial regression was used to evaluate crash frequency data. The presence of destination lighting at stop-controlled cross-intersections generally reduced the night-to-day crash ratio by 19%. The presence of treatment or destination lighting was associated with a 33%–39% increase in daytime crashes across all models but was associated with an 18%–33% reduction in nighttime crashes. Injuries in nighttime crashes decreased by 24% and total nighttime crashes reduced by 33%. Property damage crashes were reduced by 18%.

Investigation of Skew Angle and Other Factors Influencing Crash Frequency at High-Speed Rural Intersections

Intersections experience a disproportionate share of traffic crashes, injuries, and fatalities because of the increased number of conflicting traffic movements at these locations. These issues are particularly pronounced at rural locations where speeds are generally higher and most intersections are either stop- or yield-controlled. Ideally, intersecting roadways should be oriented at as close to a 90-degree angle as possible. However, intersection design can diverge from this preferred configuration and result in a skewed intersection. Skewed intersections have been found to cause safety and operational issues for road users. To determine the effect of intersection skewness on crash frequency, crash prediction models were estimated for rural stop-controlled intersections on high-speed two-lane highways throughout the state of Iowa. Separate analyses were conducted for three-leg and four-leg intersections. In both cases, crash frequency was estimated as a function of annual average daily traffic, skew angle, and other salient geometric characteristics. The results consistently showed crash frequency to increase with skew angle. A 10-degree deviation from 90 degrees would result in 3% more crashes at three-leg intersections and 4% more crashes at four-leg intersections. In addition, crashes were affected by the volume of heavy vehicles, whether the approaches were paved or unpaved and whether intersection lighting was present.

Emerging Concepts in Innovative Sign Management Programs

Transportation agencies deploy and maintain millions of traffic signs in the United States. These include regulatory, warning, guide, work zone, motorist service, recreational and cultural interest, and tourist signs. Managing these large inventories under increasing requirements for reporting, accountability, and liability has caused many transportation agencies to reexamine sign management techniques. Conventional methods of sign management, which range from paper-based systems to relational data bases, have limited capabilities and inherent inefficiencies. Additionally, liability concerns are an increasing concern for many transportation agencies. The identification and application of emerging technologies for improving sign management inventory programs are addressed. Conventional sign management practices are described, and existing technologies promising the potential for more efficient and effective sign management are discussed. Because technologies range in price and complexity, an analysis that sizes technologies to markets is presented. Rather than emphasizing the development of new technology, it is proposed that existing technologies be combined to greatly improve current sign management practices.