Geographic and Demographic Patterns of Alcohol-Related Fatal Traffic Crashes: A Spatial-Temporal Analysis in Texas, 1996-2005
Rolland, Gabriel A.
MetadataShow full item record
This thesis analyzes aggregated county-level data of fatal alcohol related traffic crashes where a driver was killed in the state of Texas during 1996 to 2005. Alcohol has constantly threatened drivers and passengers alike and continues to be a major cause of fatal crashes in Texas. Specifically, this paper targets those drivers that were killed while driving under the influence (0.01 BAC). With an increase in manageable data and the ease of availability of aggregated crash records, accident analysis can provide a closer look into trends such as spatial-temporal patterns, clustering and correlations to various factors. Furthermore, Geographic Information Systems (GIS) have enabled researchers to more efficiently interpret and study a large amount of datasets using techniques that were previously difficult or inaccessible in applications related to traffic safety and transportation. Loose-coupling of GIS with other spatial analysis programs and/or statistical software packages can now provide important results that in turn relate vital information which can be used towards understanding and potentially alleviating problems in the transportation domain. The following sections concluded that aggregated datasets at the county level are currently incomplete and do not provide the level of detail necessary to formulate a solid conclusion regarding relationships between the chosen factors and the crash dataset. Though this research was successful in mapping spatial variations and clusters, linking variables such as age, gender, location and population to the aggregated crash dataset requires more detailed information about the crash than was available. However, the objectives were successful in representing spatial-temporal patterns across the study period for all designated variables. This was an important step and solid contribution towards the representation of large datasets and their impact on policy, traffic safety, and transportation geography.