Degree Type


Date of Award


Degree Name

Doctor of Philosophy


Civil, Construction, and Environmental Engineering


Civil Engineering; Statistics

First Advisor

Anuj Sharma

Second Advisor

Lily Wang


Road crashes have been one of the major leading causes of deaths and injuries in the United States, and also bring huge financial expenses. The general theme of this dissertation is to use advanced statistical models to better understand the characteristics of crash frequency in Iowa and Nebraska, and identify important factors influencing crash frequency. It is expected that the findings of these studies could be utilized in safety improvement programs to improve traffic safety in future.

This dissertation includes three published essays. The first essay explores the spatio-temporal effects in traffic crash trend analysis under univariate cases at the macro level, where spatial and temporal effects are found to be essential in crash frequency analysis. The second essay extends the univariate spatio-temporal models into multivariate crash data, where multivariate spatio-temporal models are proved to be necessary in multivariate crash frequency analysis. The third essay examines the effects of traffic operational and roadway geometric factors on three kinds of crash types on urban midblock segments at the micro level, where segment-specific effects of these factors are revealed.


Copyright Owner

Chenhui Liu



File Format


File Size

124 pages