developing and applying sophisticated methodological approaches
associated with the analysis of crash frequency. Detailed descrip-tions and assessments of crash-frequency models can be found in
the review papers by Lord and Mannering (2010) and Mannering
and Bhat (2014). However, relatively few studies have focused on
the identification and inclusion of traditionally excluded or omit-ted variables in crash-frequency analysis. In particular, variables
related to macroscopic factors previously described (in Fig. 1) are
normally unavailable in crash databases and as a result have rarely
been examined in great detail. Mitra and Washington (2012) is one
of a few studies exploring the omitted variables in crash-frequency
modeling. The authors developed two different models of esti-mating intersection crash frequency, one with traffic volume as
the only independent variable, and the other with several spa-tial factors in addition to commonly included geometric design
and traffic factors. Through contrastive analysis of the two models,
results indicated that some spatial factors, such as local influences
of weather, sun glare, proximity to drinking establishment, prox-imity to school and demographic attributes near intersections, have
significant explanatory power and their exclusion leads to biased
estimates