Estimating automobile utilisation with panel data: An investigation of alternative assumptions for the initial conditions and error covariances

Abstract This paper illustrates how recent developments in the econometrics of panel data analysis can be implemented in the study of the dynamics of continuous choice. Adopting the household's annual use of automobiles as the empirical setting with the data defined as a four-wave panel, we outline alternative assumptions for representing the role of unobserved heterogeneity, in particular the initial conditions, and the correlational structure between the observed and unobserved influences on choice. We show the importance of treating the initial conditions as endogenous. With the growing interest in integrating discrete and continuous choice models, typically through the application of the idea of selectivity, more thought has to be given to the error structure of the continuous choice module when the panel is short, as is so often the empirical reality. The simple application of econometric methods developed for long time series can be quite misleading.