Estimation of unemployment rates in small areas of Portugal: a best linear unbiased prediction approach versus a hierarchical Bayes approach

The high level of unemployment is one of the major problems in most European countries nowadays. Hence, the demand for small area labor market statistics has rapidly increased over the past few years. The Labour Force Survey (LFS) conducted by the Portuguese Statistical Office is the main source of official statistics on the labour market at the macro level (e.g. NUTS2 and national level). However, the LFS was not designed to produce reliable statistics at the micro level (e.g. NUTS3, municipalities or further disaggregate level) due to small sample sizes. Consequently, traditional design-based estimators are not appropriate. A solution to this problem is to consider model-based estimators that "borrow information" from related areas or past samples by using auxiliary information. This paper reviews, under the model-based approach, Best Linear Unbiased Predictors and an estimator based on the posterior predictive distribution of a Hierarchical Bayesian model. The goal of this paper is to analyze the possibility to produce accurate unemployment rate statistics at micro level from the Portuguese LFS using these kinds of stimators. This paper discusses the advantages of using each approach and the viability of its implementation.

Generate disaggregated soil allocation data using a Minimum Cross Entropy Model

Montado ecosystem in the Alentejo Region, south of Portugal, has enormous agro-ecological and economics heterogeneities. A definition of homogeneous sub-units among this heterogeneous ecosystem was made, but for them is disposal only partial statistical information about soil allocation agro-forestry activities. The paper proposal is to recover the unknown soil allocation at each homogeneous sub-unit, disaggregating a complete data set for the Montado ecosystem area using incomplete information at sub-units level. The methodological framework is based on a Generalized Maximum Entropy approach, which is developed in thee steps concerning the specification of a r order Markov process, the estimates of aggregate transition probabilities and the disaggregation data to recover the unknown soil allocation at each homogeneous sub-units. The results quality is evaluated using the predicted absolute deviation (PAD) and the "Disagegation Information Gain" (DIG) and shows very acceptable estimation errors.

Combined disaggregation of agricultural land uses, livestock numbers and crops' production: an entropy approach

This paper presents several combined agricultural data disaggregation models in order to recover the farms' land uses, the livestock numbers and main crops' productions. The proposed approach estimates incomplete information at disaggregated level through entropy, using an information prior, and generating information for a combined calculation use of data in the estimation of other variables. The models were applied to the region of Algarve, to some rural pilot areas (Salir-Ameixial-Cachopo and Alcoutim) for livestock data, since this data in some Algarve's inland areas is needed for a European forest fire prevention project, and to the agrarian zones in a more complex framework. The results are promising. They were validated, in cross reference to real data, having proven to be valid and reliable. The total error was small and a considerable level of information heterogeneity was recovered. The total error was about 27,9% for the counties' land uses and 21% for the agrarian zones, and for the livestock it was also acceptable. The level of heterogeneity recovered was always higher than 50%, revealing some improvements regarding previous studies.