A Joint Methodological Approach for Interpreting School Mobility Patterns and Decisions

Earlier studies have extensively examined school mobility in regards to socio-economic and demographic dimensions. However, school travel patterns adopted by parents’ personal perceptions and attitudes have so far received scant attention, especially in the Greek com-munity. Utilizing data collected from Public Schools of Thessaloniki, Greece, through a questionnaire survey, the study presents a methodological approach followed, for interpreting the interrelations between the school mode choice and specific travel behavior characteristics. The study combines a number of statistical methods and techniques. Starting from the deployment of exploratory and confirmatory factor analysis, observed variables found to affect the school mode choice are clustered to factors that affect parents’ choices. Following, a Structural Equation Model (SEM) is shaped in order direct and indirect dependencies between the factors and the dependent variable (mode choice) to be identified. As a last step of this joint methodological approach, Artificial Neural Networks (ANNs) are trained for defining behavioral patterns leading to specific decisions in terms of school mode choice.