Theoretical requirements for calibrating gravity models

摘要: Abstract The paper examines the requirements that a gravity model should satisfy if it is to describe observed data. Two methods of fitting are considered; method maximum likelihood and least squares. It shown how depend upon sampling distribution number trips, mathematical form assumed for function separation. These more general than those put forward in other theoretical investigations. particularly concerned with appropriate when no functional specified. In such case, conventional practice has past required, without justification, be its trip length frequency agrees data, numbers trips beginning ending each zone agree totals. procedures supported some circumstances but not others. results obtained apply all types model, do on having observations possible pairs zones.