Skip to main content

Table 2 Selected models for segments

From: The variability of urban safety performance functions for different road elements: an Italian case study

Predictor Estimate Std. Error z- value p-value
All segments
 (Intercept) −6.054 0.728 −8.318 <  0.001
Ln (AADT) 0.375 0.084 4.449 <  0.001
Ln(L) 0.292 0.060 4.907 <  0.001
 Type of lanes 1: > 1 (reference: 1 lane) 0.079 0.167 0.470 0.638
Type of lanes 2: 1 + 1 (ref.: 1 lane) 0.524 0.151 3.471 <  0.001
Type of lanes 3: >  1 + 1 (ref.: 1 lane) 0.707 0.181 3.906 <  0.001
Vertical signs on driveways/minor roads (Yes - ref.: No) 0.652 0.110 5.943 <  0.001
Poor maintenance of pavements (Yes - ref.: No) −0.268 0.114 −2.348 0.019
Parking type 1: At one side (ref.: No parking) 0.218 0.131 1.668 0.095
Parking type 2: At both sides (ref.: No parking) 0.258 0.126 2.053 0.040
Parking type 3: Mixed (ref.: No parking) −1.092 0.556 −1.964 0.050
Cycle paths (Yes – ref.: No) 0.308 0.182 1.694 0.090
Goodness-of-fit measures
 LRT (reference: null model) = 200.96 (df = 11), p < .001; LRT (reference: full model) = 6.64 (df = 11), p = .828
 Nagelkerke R2 = 0.158, AIC = 2609.9
 Over-dispersion parameter (theta) = 1.08 (std. error: 0.17)
Interval of continuous predictors
 AADT: 300–29,960 vehicles/day, L: 30–1510 m
One-way segments
 (Intercept) −8.794 0.961 −9.151 <  0.001
Ln (AADT) 0.695 0.108 6.434 <  0.001
Ln(L) 0.333 0.095 3.505 <  0.001
Driveways/minor roads per km 0.010 0.003 3.163 0.002
Vertical signs on accesses/minor roads (Yes - ref.: No) 0.477 0.169 2.825 0.005
Poor maintenance of pavements (Yes - ref.: No) −0.497 0.159 −3.137 0.002
Goodness-of-fit measures
 LRT (reference: null model) = 101.68 (df = 5), p < .001; LRT (reference: full model) = 9.77 (df = 10), p = .460
 Nagelkerke R2 = 0.153, AIC = 1226.8
 Over-dispersion parameter (theta) = 1.01 (std. error: 0.26)
Interval of continuous predictors
 AADT: 300–22,600 vehicles/day, L: 30–1510 m, Density of driveways/minor roads: 0.0–142.9 number/km
Two-way segments
  (Intercept) −3.764 1.122 −3.356 <  0.001
 Ln (AADT) 0.134 0.117 1.140 0.254
Ln(L) 0.310 0.079 3.944 <  0.001
Vertical signs on accesses/minor roads (Yes - ref.: No) 0.432 0.141 3.074 0.002
Markings 1: Illegible (ref.: No/partially absent/illegible) 0.317 0.177 1.791 0.073
Markings 2: Yes (ref.: No/partially absent/illegible) 0.309 0.175 1.767 0.077
Parking type 1: At one side (ref.: No parking) 0.287 0.156 1.836 0.066
Parking type 2: At both sides (ref.: No parking) 0.441 0.152 2.903 0.004
 Parking type 3: Mixed (ref.: No parking) −0.973 0.640 −1.521 0.128
Goodness-of-fit measures
 LRT (reference: null model) = 57.69 (df = 7), p <  0.001; LRT (reference: full model) = 5.63 (df = 7), p = 0.584
 Nagelkerke R2 = 0.102, AIC = 1369.2
 Over-dispersion parameter (theta) = 1.32 (std. error: 0.29)
Interval of continuous predictors
 AADT: 1160–29,960 vehicles/day, L: 30–1415 m