【摘要】This paper formulates a multiple discrete-continuous probit (MDCP) land use modelwithin a spatially explicit economic structural framework for land use change decisions. The spatialMDCP model is capable of predicting both the type and intensity of urban development patterns overlarge geographic areas, while also explicitly acknowledging geographic proximity-based spatial depen-dencies in these patterns. At a methodological level, the paper focuses on specifying and estimating aspatial MDCP model that allows the dependent variable to exist in multiple discrete states with anintensity associated with each discrete state. The formulation also accommodates spatial dependen-cies, as well as spatial heterogeneity and heteroskedasticity, in the dependent variable, and should beapplicable in a wide variety of fields where social and spatial dependencies between decision agents (orobservation units) lead to spillover effects in multiple discrete-continuous choices (or states). A simu-lation exercise is undertaken to evaluate the ability of the proposed maximum approximate compositemarginal likelihood (MACML) approach to recover parameters from a cross-sectional spatial MDCPmodel. The results show that the MACML approach does well in recovering parameters. An empiricaldemonstration of the approach is undertaken using the city of Austin p arcel level land use data.

【文献来源】Bhat C R;Dubey S K;Alam M J B;et al.Journal of Regional Science.2015（5）