Disaggregation of spatial autoregressive processes

An aggregated Gaussian random field, possibly strong-dependent, is obtained from accumulation of i.i.d. short memory fields via an unknown mixing density phi which is to be estimated. The so-called disaggregation problem is considered, i.e. phi is estimated from a sample of the limiting aggregated field while samples of the elementary processes remain unobserved. Estimation of the density is via its expansion in terms of orthogonal Gegenbauer polynomials. After defining the estimators, their consistency and convergence rates are discussed. An example of application to beta-convergence in EU GDP per capita is discussed. (C) 2013 Elsevier B.V. All rights reserved.