An application of a switching regimes regression to the study of urban structure

The purpose of this article is to propose and highlight a statistical estimation procedure for joint identification of irregularities in population distribution in urban areas having a directional dimension, and the estimation of the parameters of the model's separate regimes. The method we propose here is an application of the switching regimes regression technique developed by Quandt (1958, 1960) for identifying the most likely allocation of n observations into two separate regimes, each associated with a different mechanism that generates its own set of observations. A subsequent purpose is to apply empirically the switching regimes method to the city of Tel-Aviv – Yafo, and discern possible regimes where population densities are generated by different processes. Received: 28 August 2000 / Accepted: 16 March 2001