An Information Theoretic Approach to Ecological Inference in Presence of Spatial Dependence

Abstract

AbstractThis chapter introduces an Information Theory (IT)-based method for modeling economic aggregates and for obtaining estimates for small area (sub-group) or subpopulations when no sample units or limited data are available. The proposed approach offers a tractable framework for modeling the underlying variation in small area indicators, in particular when data set contains outliers and in presence of collinearity among regressors since the maximum entropy estimates are robust with respect to the outliers and also less sensitive to a high condition number of the design matrix. A basic ecological inference problem which allows for spatial heterogeneity and dependence is presented with the aim of estimating small area/sub-group indicators by combining all available information at both macro and micro data level.KeywordsSpatial AutocorrelationSpatial DependenceSupport PointLocal Labour MarketSpatial Weight MatrixThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.