Statistical Approaches to Analyze Self-Reported Susceptibility to Driver Distraction

• Activity Number: 23
• Type: Topic Contributed
• Date/Time: Sunday, August 3, 2014 : 2:00 PM to 3:50 PM
• Sponsor: Government Statistics Section
• Author(s): Huei-Yen Winnie Chen*+ and Birsen Donmez and Young-Don Ko
• Companies: University of Toronto and University of Toronto and University of Toronto
• Keywords: structural equation modeling ; driver distraction ; survey ; multiple regression ; Theory of Planned Behaviour ; questionnaire

Abstract

In social and behavioural sciences, the Theory of Planned Behaviour (TPB) has been adopted in fields as diverse as advertising and healthcare to study how beliefs and attitudes can shape one's intention, and consequently action, in a particular behaviour. In driver behaviour research, for example, we have seen TPB applied successfully in predicting intentions to speed. Now we bring this theoretical model to the study of psychological constructs in driver distraction. Self-report survey using the TPB was collected from over 500 respondents from a variety of age groups (18-25, 26-40, 41-60, 61+) to examine how engagement in driver distraction may be a function of individual attitude, perceived social norms, and level of control in driving with regard to distraction. Two different statistical methods, multiple regression and structural equation modeling, are carried out to test the hypothesised relations among variables. In this talk, we will present the results side by side and discuss the pros and cons of using these two methods in analysing our dataset.