On the estimation of nonlinearly aggregated mixed models

The article proposes an iterative algorithm for the estimation of fixed and random effects of a nonlinearly aggregated mixed model. The latter arises when an additive Gaussian model is formulated at the disaggregate level on a nonlinear transformation of the responses, but information is available in aggregate form. The nonlinear transformation breaks the linearity of the aggregate model, yielding a nonlinear tight observational constraint. The algorithm rests upon the sequential linearization of the nonlinear aggregation constraint around proposals that are iteratively updated until convergence. Likelihood inferences on the hyperparameters are also discussed. As a by product we provide a solution to the problem of disaggregating over the units of analysis the aggregate responses, enforcing the nonlinear observational constraints. Illustrations are provided with reference to the temporal disaggregation problem, concerning the distribution of annual time series flows to the quarters making up the year.