Many properties of gravity models are sole consequences of the quasi-symmetry condition or its avatars. We investigate here quasi-symmetry per se, in contrast to geographical tradition, which has been more focused on the exogenous socioeconomic and spatial conditions. In particular, the ‘size – utility – accessibility’ parameterization of migration counts turn out to rely exclusively upon the quasi-symmetry of flows. Various facets of quasi-symmetry are presented and put in correspondence with Markov chains theory, Bradley – Terry – Luce decision theory, the Weidlich – Haag model, and alternative classical statistical models (marginal homogeneity, symmetry, independence). Existing as well as presumably new estimation and model selection procedures (maximum likelihood, minimum discrimination information, maximum entropy, generalized power divergence, least squares and logarithmic least squares) are discussed in a way which unifies different traditions in gravity modelling.
Get full access to this article
View all access options for this article.
References
1.
AgrestiA, 1990Categorical Data Analysis (John Wiley, New York).
2.
AndersenE B, 1990The Statistical Analysis of Categorical Data (Springer, Berlin).
3.
BavaudF, 1998, “Models for spatial weights: A systematic look”Geographical Analysis30153–171.
4.
Ben-AkivaMLermanS R, 1985Discrete Choice Analysis: Theory and Application to Travel Demand (MIT Press, Cambridge, MA).
5.
BergerJSnellJ L, 1957, “On the concept of equal exchange”Behavioral Science2111–118.
BucklewJ A, 1990Large Deviation Techniques in Decision, Simulation and Estimation (John Wiley, New York).
8.
CaussinusH, 1966, “Contribution statistique à l'analyse des tableaux de corrélation” [Statistical contribution to the analysis of correlation tables]Annales de la Faculté des Sciences de l'Université de Toulouse2977–182.
KijimaM, 1997Markov Processes for Stochastic Modelling (Chapman and Hall, London).
19.
KullbackS, 1959Information Theory and Statistics (John Wiley, New York).
20.
LuceR DSuppesP, 1965, “Preference, utility, and subjective probability”, in Handbook of Mathematical Psychology, Volume 3 Eds LuceR DBushR RGalanterE, (John Wiley, New York) pp 249–410.
21.
McCullaghP, 1982, “Some applications of quasi-symmetry”Biometrika69303–308.
22.
McCullaghPNelderJ A, 1983Generalized Linear Models (Chapman and Hall, New York).
23.
NijkampPLeitnerHWrigleyN, (Eds), 1985Measuring the Unmeasurable (Martinus Nijhoff, Dordrecht).
24.
PumainD, 1988, “France”, in International Migration Eds WeidlichWHaagG, (Springer, Berlin) pp 148–153.
25.
SchwabM GSmithT R, 1985, “Functional invariance under spatial aggregation from continuous spatial interaction models”Geographical Analysis17217–230.
26.
SenASmithT E, 1995Gravity Models of Spatial Interaction Behavior (Springer, Berlin).
27.
SmithT E, 1984, “Testable characterizations of gravity models”Geographical Analysis1674–94.
28.
SmithT EHsiehS-H, 1997a, “Gravity-type interactive Markov models—part I: A programming formulation of steady states”Journal of Regional Science37653–682.
29.
SmithT EHsiehS-H, 1997b, “Gravity-type interactive Markov models—part II: Lyapunov stability of steady states”Journal of Regional Science37683–708.
30.
SmithT RClaytonC, 1978, “Transitivity, spatially separable utility functions, and United States migration streams, 1935–1970”Environment and Planning A10399–414.
WillekensF J, 1983, “Specification and calibration of spatial interaction models: A contingency-table perspective and an application to intra-urban migration in Rotterdam”Tijdschrift voor Economische en Sociale Geografie74239–252.
35.
WilsonA G, 1974Urban and Regional Models in Geography and Planning (John Wiley, New York).
