Regional growth in Western Europe: detecting spatial misspecification using the R environment

The work discussed in Bivand and Brunstad (2003) was an attempt to throw light on apparent variability in regional convergence in relation to agriculture as a sector subject to powerful political measures, in Western Europe, 1989-1999. The present study takes up a number of points made in conclusion in that paper. Since it is possible that the non-stationarity found there is related to further missing variables, including the inadequacy of the way in which agricultural subsidies are represented, we attempt to replace the agriculture variables with better estimates of producer subsidy equivalents. It is also sensible to check that agricultural support is not masking or masked by other variables, for example human capital. The article is also an account of the development of software contributed to the R project (R Development Core Team, 2005) as packages, in particular the spdep package for spatial econometrics. New functions generously contributed by researchers will be presented and compared. We find that agricultural support does impact regional economic growth after human capital is taken into consideration, and that we can show that apparent non-stationarity is alleviated by adding these variables. We further find that the moderated remaining spatial autocorrelation can best be represented by a substantive spatial lag model.