Logistic Regression Analysis of Drivers’ Behaviour in Calabar Metropolis, Cross River State, Nigeria

Abstract

The paper applied the driver behaviour questionnaire with closed-ended questions on drivers in locations purposively sampled to reflect different landuse categories. Socio-economic characteristics of drivers and travel behaviour were contained in the DBQ. Logistic regression analysis was conducted to predict the behaviour of drivers for 347 household heads (90.4% success rate) using reasons for violation traffic, gender, age, education ownership of valid driver license and driver category as predictors. A test of the full model against a constant only model was statistically significant, indicating that the predictors as a set reliably distinguished between traffic violators and non-traffic violators (chi square = 89.113, p < .001 with df = 8). Prediction success overall was 94.2% (91.3% for non-violation and 96.2% for traffic violation. The Wald criterion demonstrated that impatience, emergency, weak law, and other factors made a significant contribution to prediction in model 1 (p = .000), while only ignorance did not (p = .999). The study in line with reviewed literature has shown that when traditional cities increase in population and level of commercial activities, there is bound to be mobility conflicts if not properly managed. Enforcement of traffic laws, strategies directed at improving the safety management system, road safety awareness campaigns, among others were recommended.