Journal of Advanced Transportation

Research Article

Modeling Injury Severity for Nighttime and Daytime Crashes by Using Random Parameter Logit Models Accounting for Heterogeneity in Means and Variances

Table 5

Model results of the random parameter logit model with heterogeneity in means and variance for all crashes.
VariablesParameter estimatet-statElasticity effect
Light injuryMinor injurySevere injury
[MI] constant−3.65−3.37   
Crash characteristics
 [MI] pavement1.252.650.00150.0011−0.0026
Traffic characteristics
 [SI] AADT−5.25 × 10−5-2.810.0227−0.0062−0.0165
Speed characteristics
 [SI] −0.024−3.235.83 × 10−52.51 × 10−5−8.34 × 10−5
 [SI] 0.0482.59−5.42 × 10−5−3.13 × 10−58.55 × 10−5
Geometric characteristics
 [LI] 2.91 × 10−42.311.87 × 10−3−2.33 × 10−30.46 × 10−3
 [LI] 3.06 × 10−32.191.06 × 10−30.68 × 10−3−1.74 × 10−3
Random parameters
 [MI] constant−4.65−4.17   
 Standard deviation4.633.97   
Heterogeneity in the means of random parameter
 [MI] constant −3.42 × 10−3−4.51   
Heterogeneity in the variances of random parameter
 [MI] constant 0.0684.41   
 Number of observations3159    
 Number of estimated parameters60    
 Log-likelihood−256.24    
 AIC641.84    
 BIC947.48    
 R20.23