Multi-level hot zone identification for pedestrian safety

Macro and micro models for zonal crash prediction with application in hot zones identification

“…In accordance with Aguero-Valverde (2013),Lee (2014),Lee et al, (2015), the hot zones in this study refer to the areas with promise. The "zone" is used here to present the fact that the basic spatial units adopted in these studies are pre-defined geography units (e.g., TAZs, zip codes, or cantons).…”

“…Potential for safety improvement (PSI) is adopted here for the ranking of hot zones, which is defined as the difference between crash frequency expectation at the zone and the expectation at the similar zones (Aguero-Valverde and Jovanis, 2010; Aguero-Valverde, 2013; Dong et al, 2016;Lee et al, 2015). The measure could effectively identify whether a zone suffers more number of crashes compared with other zones with similar characteristics.…”

“…Hot zones are defined as those with a top 10% PSI, warm zones refer to the ones with a PSI between 0 and top 10%, and the remaining could be treated as the cold zones. 10% was commonly used as the threshold (Cheng and Washington, 2008;Lee, 2014;Lee et al, 2015), and it could be added to 20% if one wants to address more areas with higher crash risk. As a result, there are overall 9 combination classifications: HH, HW, HC, WH, WW, WC, CH, CW, and CC.…”

“…the expected crash frequency in TAZ i at time t), β is the vector of coefficient estimates. The variables of daily vehicle miles traveled (DVMT) and total population are simultaneously selected as the measures of exposure, as the model with combination of exposure variables outperforms the counterpart with a single exposure measure (Pirdavani et al, 2012;Lee et al, 2015). Hence:…”

Spatiotemporal and random parameter panel data models of traffic crash fatalities in Vietnam

“…spatial dependence or correlation and spatial heterogeneity (Anselin, 1988), have been considered in macro-level safety analyses. For example, Bayesian spatial approaches have been used to account for possible spatial correlation between areas (Aguero-Valverde and Jovanis, 2006;Quddus, 2008;Siddiqui et al, 2012;Wang et al, 2013;Xu et al, 2014;Dong et al, 2015;Lee et al, 2015;Song et al, 2015;Siddiqui and Watkins, 2016). To consider spatial heterogeneity, previous macro-level safety studies have adopted the geographically weighted regression (GWR) models (Hadayeghi et al, 2003;Erdogan, 2009;Hadayeghi et al, 2010;Li et al, 2013) and random parameter models (Coruh et al, 2015;Xu and Huang, 2015).…”