Pj. Boyle et R. Flowerdew, MODELING SPARSE INTERACTION MATRICES - INTERWARD MIGRATION IN HEREFORD AND WORCESTER, AND THE UNDERDISPERSION PROBLEM, Environment & planning A, 25(8), 1993, pp. 1201-1209
Recently, it has been argued that migration models in which ordinary l
east squares regression is used are inappropriate, because the depende
nt variable (number of migrants) is a count. Instead, a Poisson regres
sion approach can be adopted. Goodness of fit can be evaluated by usin
g a deviance (log-likelihood) or X2 statistic, whose significance can
be compared with a chi2 distribution with appropriate degrees of freed
om. In this paper, such an approach is used to model ward-level migrat
ion flows within the county of Hereford and Worcester. However, it is
shown that for this exceedingly sparse data set the deviance figures a
ttained are very low, suggesting that there may be a problem of underd
ispersion. This is in contrast to the overdispersion which has been id
entified as a common problem in Poisson models. The low deviance figur
es arise from the large number of zeros and small flows in the data ma
trix, which invalidate the usual chi2 goodness-of-fit test. A simulati
on approach to the assessment of model goodness of fit is suggested, a
nd the results from applying it to the Hereford and Worcester data set
are described.