Research Article

Distinguishing between Rural and Urban Road Segment Traffic Safety Based on Zero-Inflated Negative Binomial Regression Models

Table 5

Parameter estimates of ZINB model for injury and fatal crash frequency.

ParameterDFEstimateStandard errort valueP value

Negative binomial regression part

Intercept1−1.2720.093−13.73<0.0001
Numberofla (2 lane)0
Numberofla (4 lane)1−0.3980.098−4.08<0.0001
RoU (rural)1−0.2320.118−1.960.0496
RoU (urban)0
ADT_100010.0600.00415.58<0.0001
LENGTH10.3380.0685.00<0.0001

Logistic regression part

Inf_Intercept15.4040.8506.35<0.0001
Numberofla (2 lane)0
Numberofla (4 lane)1−0.9670.352−2.750.0060
Inf_ADT_10001 0.035 0.016 2.21 0.0268
Inf_LENGTH1−38.3256.436−5.95<0.0001
_Alpha1 1.073 0.1248.64<0.0001