Research Article
Modeling Injury Severity for Nighttime and Daytime Crashes by Using Random Parameter Logit Models Accounting for Heterogeneity in Means and Variances
Table 7
Model results of the random parameter logit model with heterogeneity in means and variance for nighttime crashes.
| | Variables | Parameter estimate | t-stat | Elasticity effect | | Light injury | Minor injury | Severe injury |
| | Crash characteristics | | [MI] season | −0.56 | −2.91 | 0.0019 | −0.0027 | 0.0008 | | [MI] pavement | −2.11 | −2.58 | 0.0009 | −0.0004 | −0.0005 | | Speed characteristics | | [SI] | 0.037 | 3.21 | −6.48 × 10−5 | −0.16 × 10−5 | 6.64 × 10−5 | | Geometric characteristics | | [Mi] | 8.86 × 10−4 | 4.63 | −1.19 × 10−3 | 1.72 × 10−3 | −0.53 × 10−3 | | [Mi] | 3.00 × 10−3 | 2.27 | 1.47 × 10−3 | 0.34 × 10−3 | −1.81 × 10−3 | | Random parameters | | [MI] constant | −9.26 | −4.30 | | | | | Standard deviation | 3.68 | 3.15 | | | | | Heterogeneity in the means of random parameter | | [LI] constant | 8.19 × 10−3 | 4.67 | | | | | [MI] constant | −5.16 × 10−3 | −3.51 | | | | | Heterogeneity in the variances of random parameter | | [LI] constant | −3.86 × 10−4 | −2.38 | | | | | Number of observations | 935 | | | | | | Number of estimated parameters | 24 | | | | | | Log-likelihood | −100.13 | | | | | | AIC | 316.27 | | | | | | BIC | 615.87 | | | | | | R2 | 0.26 | | | | |
|
|
