Testing Goodness-of-Fit with the Kernel Density Estimator: GoFKernel

A problem that frequently arises in economics, demography, statistics, transportation planning and stochastic modelling is how to adjust the entries of a matrix to fulfil row and column aggregation constraints. Biproportional methods in general and the so-called RAS algorithm in particular, have been used for decades to find solutions to this type of problem. Although alternatives exist, the RAS algorithm and its extensions are still the most popular. Apart from some interesting empirical and theoretical properties, tradition, simplicity and very low computational costs are among the reasons behind the great success of RAS. Nowadays computer hardware and software have made alternative procedures equally attractive. This work analyses, through simulation, the performance of RAS and some minimands when matrix coefficients vary following different schemes of change. Results suggest RAS algorithm as the best option when variations in coefficients are proportional to their size, while the method based on minimizing squared differences is seen to be the best alternative when the standard deviations of variations are either constant, variable, or an inverse function of matrix entries.

An empirical two-equation dynamic panel-data model system with fixed effects is proposed to analyze the relationship between knowledge creation and economic performance across regions over time. Estimates of the model for Spanish regions show that (i) knowledge creation depends on local R&D effort, on the amount of knowledge in use, and on knowledge creation in neighboring regions; and (ii) assimilation of new knowledge depends on local knowledge creation and on assimilation of knowledge in neighboring regions. Both processes include region-specific context fixed effects and region-specific time effects, representing region-specific dynamic influences. The results imply that (a) efficiency gains at regional level may be achieved by investing locally in the creation of new knowledge, either technological or organizational; (b) creation of knowledge in a region may be promoted by using greater amounts of already existing knowledge, as well as by increasing local R&D effort; (c) both knowledge creation and knowledge assimilation spread to/from neighboring regions; and (d) regional contexts influence both knowledge creation and knowledge assimilation separately.