Generalized Akaike information to estimate the employed people by economic activity

E. López Vizcaíno, M. J. Lombardía Cortiña, C. Rueda Sabater

The aim of this work is to estimate the employment people in Galicia, by economic activity and quarter, using data from Labour Force Survey. Several small area model-based estimators are considered, which are derived from additive regression models. When estimators that only borrow strength across areas are considered, the trend pattern across time depends on the characteristics of the area and the model used to derive the estimators. Often, for a given area and model, the time trend pattern is more abrupt than desired. On the other side, when time series models are considered too smoothed patterns are generated and prevent major trend changes being detected. We propose a very different and simple strategy to borrow strength across time, as well as across areas, that lacks these drawbacks. The proposal makes use of a Generalized Akaike Information Criteria (GAIC) measure. The idea is select the model using the area-specific component of an aggregated GAIC measure across time.

Palabras clave: AIC, small area, Galicia, Fay-Herriot, spline model, monotone model

M05.4 Sesión de la Sociedad Gallega para la Promoción de la Estadística y la Investigación Operativa
6 de septiembre de 2016  11:00
Aula 21.07

J. Rodríguez Veiga, I. Gómez Costa, M. J. Ginzo Villamayor, B. V. Casas Méndez, J. L. Saiz Díaz

A. Vaamonde Liste, M. Meijide Vecino, P. Sanchez Bello, R. Luaces Pazos, P. Sanchez Fernandez

M. P. Romero Martínez, E. López Vizcaíno