方法对比

	空间交互（引力）模型	区位-分配模型	多项逻辑回归
领域	空间分析	空间分析	计量经济学
方法族	Regression model	Process / pipeline	Regression model
起源年份	1971	1963	1974
提出者	Alan Wilson (entropy-maximizing family)	Leon Cooper; S. L. Hakimi	McFadden
类型	Model of flows between spatial origins and destinations	Spatial facility-location optimization	Multinomial logistic regression
开创性文献	Wilson, A. G. (1971). A family of spatial interaction models, and associated developments. Environment and Planning A, 3(1), 1–32.	Cooper, L. (1963). Location-allocation problems. Operations Research, 11(3), 331–343.	McFadden, D. (1974). Conditional Logit Analysis of Qualitative Choice Behavior. In P. Zarembka (Ed.), Frontiers in Econometrics (pp. 105-142). Academic Press. ISBN: 978-0127761503
别名	gravity model, spatial interaction model, competing destinations model, mekânsal etkileşim modeli	facility location, p-median problem, maximal covering location problem, yer-tahsis modelleri	multinomial logistic regression, polytomous logistic regression, softmax regression, Çok Kategorili Lojistik Regresyon
相关	4	4	5
摘要	Spatial interaction models predict the volume of flows — migrants, commuters, shoppers, trade, trips — between origins and destinations as a function of the size of each place and the distance or cost separating them. By analogy to Newton's gravity, interaction rises with the 'mass' of origin and destination and falls with separation, and Wilson's 1971 entropy-maximizing family put these models on a rigorous footing for transport, migration, and retail analysis.	Location-allocation models decide where to place a set of facilities and simultaneously assign demand points to them so as to optimize an objective such as total travel cost, worst-case distance, or population covered. Rooted in the operations-research work of Cooper (1963) and Hakimi (1964) and central to network GIS, they answer questions like where to site warehouses, hospitals, fire stations, or schools to best serve a spatially distributed population.	Multinomial logistic regression is a maximum-likelihood method for a nominal (unordered) dependent variable with more than two categories. Building on McFadden's 1974 treatment of qualitative choice, it gives each category its own set of coefficients relative to a reference category.