Development of Accident Frequency Models with Random Parameters on Interstate Roadway Segments with and without Lighting Systems
Table 3
Model results for segments with lighting systems.
Variable
Constant parameter
Random parameter
Mean
t-statistic
Distribution
Mean
t-statistic
Standard deviation
t-statistic
Constant
−11.073
−38.938
n.a.
Exposure
Logarithm of averaged daily traffic volume
1.305
43.889
n.a.
Logarithm of segment length
n.a.
Normal
0.075
3.452
0.073
4.398
Lanes
Proportion of segments with standard number of lanes
0.321
6.845
n.a.
Proportion of segment with low number of lanes
n.a.
Normal
0.094
4.521
0.281
3.661
Left shoulder width
Proportion of segments with low left shoulder width
0.040
3.608
n.a.
Proportion of segments with standard left shoulder width
n.a.
Normal
−0.020
−4.245
0.009
4.320
Right shoulder width
Proportion of segments with standard right shoulder width
−0.033
−10.127
n.a.
Curves
Number of horizontal curves in segment
0.065
5.593
n.a.
Number of vertical curves in segment
0.047
2.897
n.a.
Scale parameter for overdispersion
3.806
21.642
n.a.
Number of observations: 205. McFadden’s pseudo : 0.66. Log likelihood at convergence of RPNB model: −5,719.93. Log likelihood at the constant only: −16,959.74. n.a.: not applicable.