Innovative Analysis for Reducing Data Using a Tracking Methodology
Is Version Of
Every year the National Highway Traffic Safety Administration (NHTSA) publishes its finding of crash statistics and, in the latest data from 2010, speeding was a factor in 31% of the traffic fatalities in 2010(NHTSA Speeding, 2010). As a surrogate for speed safety, reductions in speeds statistics are used to determine whether treatments are effective at improving safety. The issue with this type of analysis is that the treatments are directed toward a specific user and by using all vehicles data, some vehicles not affected by the treatment are included in the analysis.
To mitigate these vehicles, tracking may be used to reduce the data collected to only the affected vehicles. This provides more accurate and precise data when evaluating the effectiveness of the treatment. Limited research has been completed for tracking, because of this it is unknown whether reducing the data will provide any statistical difference as well as indicators for when tracking should be used. The objective of this thesis is to determine difference using a standard method and tracking method as well as provide indicators of when tracking should be used. In addition, a speed reduction method will be analyzed as well to determine a separate safety surrogate measure.
Using two current research projects for the analysis, traffic calming and curve safety, the standard method and tracking method were compared. The results showed that the standard method both under- and over-estimated the effectiveness of the treatments depending on the site location. After reviewing the data the access points around the treatment provided an indicator for when the speed statistics were statistically different using the tracking method. This was expected because of turning movements created by such points that affect the vehicles speeds. Upstream speeds were the other indicator found that had an effect on the data. In this situation it affected the speed reduction statistics that were calculated with tracking vehicles. These statistics provided a detailed view of where vehicles speeds were being reduced that would not be capable with the standard method. Overall, the objectives of the thesis were met by showing that tracking vehicles does have an effect on speed statistics. Indicators were found but further research must be completed to determine other possible indicators as well as other possible ways to reduce data.