Skip to main content

An Open Access Journal

Table 5 Multinomial logit model of three different crash types (reference type = run-off crash); sample = mainly responsible car drivers involved in a motorway crash; predictors = age and gender (reference gender = male)

From: Relationships between risk of causing a motorway crash in Austria and attributes of drivers

Variable

Parameter estimate

Robust

std. error

Robust

t-value

p-value

const. of alt. 1 = run-off crash

0.000

   

const. of alt. 2 = rear-end crash

−1.085

0.213

−5.089

0.000

const. of alt. 3 = lane change crash

−3.195

0.363

−8.795

0.000

age on alt. 2

0.053

0.010

5.082

0.000

age-squared on alt. 2

−0.001

0.000

−4.797

0.000

gender = female on alt. 2

−0.492

0.075

−6.517

0.000

age on alt. 3

0.065

0.017

3.839

0.000

age-squared on alt. 3

−0.001

0.000

−3.301

0.001

gender = female on alt. 3

−0.101

0.125

−0.811

0.417

  1. Number of observations: 3841
  2. null log-likelihood: − 4219.770
  3. constant log-likelihood: − 3547.572
  4. final log-likelihood: − 3505.007
  5. McFadden’s rho squared: 0.169