Estimating unemployment in very small areas
In the last few years, European countries have shown a deep interest in applying small area techniques to produce reliable estimates at county level. However, the specificity of every European country and the heterogeneity of the available auxiliary information, make the use of a common methodology...
| Autores: | , , , |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2009 |
| País: | España |
| Institución: | Universitat Politècnica de Catalunya (UPC) |
| Repositorio: | UPCommons. Portal del coneixement obert de la UPC |
| Idioma: | inglés |
| OAI Identifier: | oai:upcommons.upc.edu:2099/8938 |
| Acceso en línea: | https://hdl.handle.net/2099/8938 |
| Access Level: | acceso abierto |
| Palabra clave: | Sampling (Statistics) Mathematical statistics Regression analysis Finite population Prediction theory Labour Force Survey Mostreig (Estadística) Estadística matemàtica Classificació AMS::62 Statistics::62D05 Sampling theory, sample surveys Classificació AMS::62 Statistics::62J Linear inference, regression Classificació AMS::62 Statistics::62F Parametric inference Àrees temàtiques de la UPC::Matemàtiques i estadística::Estadística matemàtica |
| Sumario: | In the last few years, European countries have shown a deep interest in applying small area techniques to produce reliable estimates at county level. However, the specificity of every European country and the heterogeneity of the available auxiliary information, make the use of a common methodology a very difficult task. In this study, the performance of several design-based, model-assisted, and model-based estimators using different auxiliary information for estimating unemployment at small area level is analyzed. The results are illustrated with data from Navarre, an autonomous region located at the north of Spain and divided into seven small areas. After discussing pros and cons of the different alternatives, a composite estimator is chosen, because of its good trade-off between bias and variance. Several methods for estimating the prediction error of the proposed estimator are also provided. |
|---|