Robin Flowerdew

Using areal interpolation methods in geographic information systems

This paper reports on a research project concerned with the areal interpolation problem — the problem of comparing different data sets when they have been made available for different zonal systems. Our approach is based on using additional information to guide the interpolation process. This paper emphasizes recent work applying the method to Poisson and binomially distributed data. There is also discussion of how the method can best be implemented in a geographic information system.

The effect of data aggregation on a Poisson regression model of Canadian migration

A Statistics Canada data set for Canadian migration data at the census division level incorporating information on income tax for 1986 has already been presented. This matrix of 260 × 260 flows was used to calibrate a set of Poisson regression models by utilizing flows for the aggregate population. In this paper, the relatively high spatial resolution is used to test for aggregation effects as the original 260 units are combined to form fewer, synthetic regions with larger areas. A series of simulation experiments are performed with three different aggregation algorithms to create 130, 65, and ultimately 10 (corresponding to the provinces) synthetic regions. Average results from the experiments are compared with the original model. Results are obtained that suggest that, in this case, obvious aggregation effects similar to those observed elsewhere (by Openshaw) are not observed.

Methodological problems in the generation of household waste statistics: An analysis of the United Kingdom's National Household Waste Analysis Programme

Abstract The establishment of national targets designed to bring about more sustainable waste management in many developed countries has not generally been accompanied by the creation of reliable information systems for policy formulation and monitoring. In the first part of this paper the factors that complicate the collection of reliable household waste statistics are examined from both applied and theoretical perspectives. The second part presents a critique of the recent UK National Household Waste Analysis Programme (NHWAP). This was based on waste-collection-round samples selected by means of a geodemographie classification package (ACORN). NHWAP data are currently the only national data on household waste composition and the results have already been widely used by policy-makers at national and local levels. However, it is concluded that the NHWAP sample was too limited for there to be much confidence in the results. A national research programme based on household samples is required in order to understand the relationships between household waste arisings and socioeconomic, institutional, spatial and temporal variables. An outline methodology is suggested.

Migration between labour market areas in Great Britain, 1970–1971

Flowerdew R. and Salt J. (1979) Migration between labour market areas in Great Britain, 1970–1971, Reg. Studies 13, 211–231. Using a set of 126 areal units (Standard Metropolitan Labour Areas) intended to represent labour markets, this paper describes and analyses 1970–71 migration flows. It begins with a description of the most important flows between labour market areas, in both absolute and relative terms. The effects of labour market size are removed by a transaction flow analysis, and the effects of distance and size are evaluated by a gravity model. The largest residuals from the gravity model are then identified and discussed in terms of economic and other explanatory factors.

Reacting to Ground Truth

Ground Truth, a set of papers, edited by John Pickles, about the social implications of GIS, has contributed to the revival of an old debate between qualitative and quantitative approaches in human geography, This paper is intended to be a contribution to the debate: reactions and reflections triggered by the book rather than a review or evaluation of it. After acceptance of some of the criticisms of GIS and quantitative geography, attempts are made to defend them against other criticisms, and the paper concludes with some hopes for how the debate will continue.

Migration of elderly people to join existing households: some evidence from the 1991 Household Sample of Anonymised Records

In this paper the extent to which migration of the elderly is linked to changing family living situations is explored. The work described is part of a larger project concerned with the relationship between migration, kinship, and household change. Discussions of the living arrangements of older people have often referred to moves made to join adult children or other relatives. In this paper we use the Household Sample of Anonymised Records to investigate moves of this type. The Sample of Anonymised Records allows the identification of individuals who have joined already existing households within the previous year. We make use of information on people over 65 years in Great Britain who have changed address in the previous year but are now part of a household some of whose members have not moved. This paper is confined to the limited range of information available from the 1991 census but it does allow us to estimate the number of older people making moves of this type, and to identify their age, sex, and marital status, and their relationship to the household they have joined. It is also possible to say something about the households which these people are joining, in terms of tenure and house type, and to describe the distribution of distances moved. Although the data do not allow direct inferences about whether these moves are related to the needs of the old people for care, the census question on limiting long-term illness provides data relevant to this issue.

Modelling sparse interaction matrices: interward migration in Hereford and Worcester, and the underdispersion problem.

Recently, it has been argued that migration models in which ordinary least squares regression is used are inappropriate, because the dependent variable (number of migrants) is a count. Instead, a Poisson regression approach can be adopted. Goodness of fit can be evaluated by using a deviance (log-likelihood) or X2 statistic, whose significance can be compared with a χ2 distribution with appropriate degrees of freedom. In this paper, such an approach is used to model ward-level migration flows within the county of Hereford and Worcester. However, it is shown that for this exceedingly sparse data set the deviance figures attained are very low, suggesting that there may be a problem of underdispersion. This is in contrast to the overdispersion which has been identified as a common problem in Poisson models. The low deviance figures arise from the large number of zeros and small flows in the data matrix, which invalidate the usual χ2 goodness-of-fit test. A simulation approach to the assessment of model goodness of fit is suggested, and the results from applying it to the Hereford and Worcester data set are described.

The Standard Spending Assessment as a Measure of Spending Needs in Nonmetropolitan Districts

Central government assistance to local government in England is based on the Standard Spending Assessment (SSA), which is intended to reflect the spending needs of each local council. This paper is an evaluation of the methodology used in calculating SSA, with particular reference to the district-level service clement of the All Other Services block of SSA. This element accounts for the vast majority of SSA for nonmetropolitan district councils. The first section of the paper is concerned with the overall structure of the SSA methodology, and the second section is an examination of some of the details of how it was implemented. Barrow-in-Furness is used as an illustrative example. In the conclusion some specific problems are high-lighted and some potential improvements are suggested.

Some applications of Murphy's law: using computers for geography practical teaching

Abstract We have used computers in geography practicals for several years and our efforts in this direction have helped us isolate several new applications of Murphys Law. We review some of our discoveries in the areas of classroom demonstrations and hands‐on practicals, in terms of hardware, software and ‘liveware’. In general, we share others’ enthusiasm for using computers in teaching, but we are convinced that such usage will normally be liable to subversion by Murphys Law. Teaching using computers is harder because of the need for careful presentation and contingency planning and the necessity to improvise when Murphys Law strikes!

Migration models incorporating interdependence of movers

Models of migration between regions are often based on the assumption that individual moves can be modelled by a Poisson distribution whose parameter is a function of origin and destination characteristics, and generalized cost; this is true of Poisson regression models and spatial interaction models. The Poisson assumption is that each individual acts independently from others making the same move. In fact, migration is usually engaged in by household groups, not independent individuals, making the Poisson assumption invalid. It is possible instead to construct a model in which the probability of a household moving is given by a Poisson model and the number of individuals in a moving household is given by an observed household-size distribution. This generalized Poisson model is explained and fitted to a set of data on local-level migration within the English county of Hereford and Worcester. However, the sparse nature of the data set raises problems in assessing goodness of fit because the deviance value is unusually low. This is tackled here with a simulation methodology.