This paper describes the first phase of a study of the impact of key events on long-term transport mode choice decisions. The suggested complexity of transport mode choice is modeled with a Bayesian decision network. An Internet-based questionnaire was designed to measure the various conditional probability tables and the conditional utility tables of the Bayesian decision network. Seven key events were implemented in the questionnaire: change in residential location, change in household composition, change in work location, change in study location, change in car availability, change in availability of public transport pass, and change in household income. Data from 554 respondents were used to illustrate how the tables can be constructed on the basis of event history data.