MODELING RESIDENTIAL CHOICE*
提出一种结合随机选择模型与数学规划的居住选址模拟新方法，区分事前与事后选择概率，并在蒙特利尔大都市区测试了人口老龄化与家庭规模缩小的影响。
ABSTRACT. This paper presents a new approach in the modeling of residential choices for simulation purpose. The originality of the approach resides in the way recent developments in stochastic choice models are combined with deterministic mathematical programming which allows to define an equilibration process for simulation. In that respect, ex ante probabilities of housing choice based on random utility maximization under perceived constraints are distinguished from ex post probabilities of choice that respect supply constraints. The proposed model is tested on the Montreal Metropolitan Region, and a few simulation results based on a scenario of population aging and decrease in household size are analyzed.