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.

Estimação em pequenos domínios com modelos espaciotemporais de nível área

Tese dout., Métodos Quantitativos Aplicados à Economia e à Gestão, Universidade do Algarve, 2009

Predição em modelos de tempo de falha acelerado com efeito aleatório para avaliação de riscos de falha em poços petrolíferos

We considered prediction techniques based on models of accelerated failure time with random e ects for correlated survival data. Besides the bayesian approach through empirical Bayes estimator, we also discussed about the use of a classical predictor, the Empirical Best Linear Unbiased Predictor (EBLUP). In order to illustrate the use of these predictors, we considered applications on a real data set coming from the oil industry. More speci - cally, the data set involves the mean time between failure of petroleum-well equipments of the Bacia Potiguar. The goal of this study is to predict the risk/probability of failure in order to help a preventive maintenance program. The results show that both methods are suitable to predict future failures, providing good decisions in relation to employment and economy of resources for preventive maintenance.

Estimación de variables dasométricas a partir de datos LiDAR y obtención de modelos de referencia para las distribuciones de alturas y diámetros del arbolado

La Gestión Forestal Sostenible se define como “la administración y uso de los bosques y tierras forestales de forma e intensidad tales que mantengan su biodiversidad, productividad, capacidad de regeneración, vitalidad y su potencial para atender, ahora y en el futuro, las funciones ecológicas, económicas y sociales relevantes a escala local, nacional y global, y que no causan daño a otros ecosistemas” (MCPFE Conference, 1993). Dentro del proceso los procesos de planificación, en cualquier escala, es necesario establecer cuál será la situación a la que se quiere llegar mediante la gestión. Igualmente, será necesario conocer la situación actual, pues marcará la situación de partida y condicionará el tipo de actuaciones a realizar para alcanzar los objetivos fijados. Dado que, los Proyectos de Ordenación de Montes y sus respectivas revisiones son herramientas de planificación, durante la redacción de los mismos, será necesario establecer una serie de objetivos cuya consecución pueda verificarse de forma objetiva y disponer de una caracterización de la masa forestal que permita conocer la situación de partida. Esta tesis se centra en problemas prácticos, propios de una escala de planificación local o de Proyecto de Ordenación de Montes. El primer objetivo de la tesis es determinar distribuciones diamétricas y de alturas de referencia para masas regulares por bosquetes, empleando para ello el modelo conceptual propuesto por García-Abril et al., (1999) y datos procedentes de las Tablas de producción de Rojo y Montero (1996). Las distribuciones de referencia obtenidas permitirán guiar la gestión de masas irregulares y regulares por bosquetes. Ambos tipos de masas aparecen como una alternativa deseable en aquellos casos en los que se quiere potenciar la biodiversidad, la estabilidad, la multifuncionalidad del bosque y/o como alternativa productiva, especialmente indicada para la producción de madera de calidad. El segundo objetivo de la Tesis está relacionado con la necesidad de disponer de una caracterización adecuada de la masa forestal durante la redacción de los Proyectos de Ordenación de Montes y de sus respectivas revisiones. Con el fin de obtener estimaciones de variables forestales en distintas unidades territoriales de potencial interés para la Ordenación de Montes, así como medidas de la incertidumbre en asociada dichas estimaciones, se extienden ciertos resultados de la literatura de Estimación en Áreas Pequeñas. Mediante un caso de estudio, se demuestra el potencial de aplicación de estas técnicas en inventario forestales asistidos con información auxiliar procedente de sensores láser aerotransportados (ALS). Los casos de estudio se realizan empleando datos ALS similares a los recopilados en el marco del Plan Nacional de Ortofotografía Aérea (PNOA). Los resultados obtenidos muestran que es posible aumentar la eficiencia de los inventarios forestales tradicionales a escala de proyecto de Ordenación de Montes, mediante la aplicación de estimadores EBLUP (Empirical Best Linear Unbiased Predictor) con modelos a nivel de elemento poblacional e información auxiliar ALS similar a la recopilada por el PNOA. ABSTRACT According to MCPFE (1993) Sustainable Forest Management is “the stewardship and use of forests and forest lands in a way, and at a rate, that maintains their biodiversity, productivity, regeneration capacity, vitality and their potential to fulfill, now and in the future, relevant ecological, economic and social functions, at local, national, and global levels, and that does not cause damage to other ecosystems”. For forest management planning, at any scale, we must determine what situation is hoped to be achieved through management. It is also necessary to know the current situation, as this will mark the starting point and condition the type of actions to be performed in order to meet the desired objectives. Forest management at a local scale is no exception. This Thesis focuses on typical problems of forest management planning at a local scale. The first objective of this Thesis is to determine management objectives for group shelterwood management systems in terms of tree height and tree diameter reference distributions. For this purpose, the conceptual model proposed by García-Abril et al., (1999) is applied to the yield tables for Pinus sylvestris in Sierra de Guadrrama (Rojo y Montero, 1996). The resulting reference distributions will act as a guide in the management of forests treated under the group shelterwood management systems or as an approximated reference for the management of uneven aged forests. Both types of management systems are desirable in those cases where forest biodiversity, stability and multifunctionality are pursued goals. These management systems are also recommended as alternatives for the production of high quality wood. The second objective focuses on the need to adequately characterize the forest during the decision process that leads to local management. In order to obtain estimates of forest variables for different management units of potential interest for forest planning, as well as the associated measures of uncertainty in these estimates, certain results from Small Area Estimation Literature are extended to accommodate for the need of estimates and reliability measures in very small subpopulations containing a reduced number of pixels. A case study shows the potential of Small Area Estimation (SAE) techniques in forest inventories assisted with remotely sensed auxiliary information. The influence of the laser pulse density in the quality of estimates in different aggregation levels is analyzed. This study considers low laser pulse densities (0.5 returns/m2) similar to, those provided by large-scale Airborne Laser Scanner (ALS) surveys, such as the one conducted by the Spanish National Geographic Institute for about 80% of the Spanish territory. The results obtained show that it is possible to improve the efficiency of traditional forest inventories at local scale using EBLUP (Empirical Best Linear Unbiased Predictor) estimators based on unit level models and low density ALS auxiliary information.

Likelihood prediction for generalized linear mixed models under covariate uncertainty

This paper presents the techniques of likelihood prediction for the generalized linear mixed models. Methods of likelihood prediction is explained through a series of examples; from a classical one to more complicated ones. The examples show, in simple cases, that the likelihood prediction (LP) coincides with already known best frequentist practice such as the best linear unbiased predictor. The paper outlines a way to deal with the covariate uncertainty while producing predictive inference. Using a Poisson error-in-variable generalized linear model, it has been shown that in complicated cases LP produces better results than already know methods.

Estimação jackknife ponderada do erro quadrático médio de predição do EBLUP temporal

A metodologia baseada na melhor predição linear empírica não enviesada (Empirical Best Linear Unbiased Prediction), consagrada com o acrónimo EBLUP, é muito utilizada na estimação de parâmetros para pequenos domínios. Apesar da relativa facilidade de dedução dos EBLUPs, mesmo num contexto de um modelo longitudinal, a medição da sua qualidade é um problema complexo devido à di culdade de estimação do erro quadrático médio de predição (EQMP) de tais preditores. Neste trabalho utiliza-se um estimador de parâmetros de interesse em pequenos domínios assistido pelo modelo temporal de Rao-Yu (Rao e Yu, 1994). O EBLUP temporal é apresentado e é revisitada a aproximação analítica assimptótica do EQMP do EBLUP temporal proposta por Rao e Yu (1994). Sob o modelo de Rao-Yu, é proposta uma metodologia jackknife ponderada para estimar o EQMP do EBLUP, desenvolvida a partir dos trabalhos de Chen e Lahiri (2008). Foi realizado um estudo por simulação com o objectivo de comparar o desempenho do estimador proposto com o obtido por via da aproximação analítica do EQMP.

Inférence robuste à la présence des valeurs aberrantes dans les enquêtes

Cette thèse comporte trois articles dont un est publié et deux en préparation. Le sujet central de la thèse porte sur le traitement des valeurs aberrantes représentatives dans deux aspects importants des enquêtes que sont : l’estimation des petits domaines et l’imputation en présence de non-réponse partielle. En ce qui concerne les petits domaines, les estimateurs robustes dans le cadre des modèles au niveau des unités ont été étudiés. Sinha & Rao (2009) proposent une version robuste du meilleur prédicteur linéaire sans biais empirique pour la moyenne des petits domaines. Leur estimateur robuste est de type «plugin», et à la lumière des travaux de Chambers (1986), cet estimateur peut être biaisé dans certaines situations. Chambers et al. (2014) proposent un estimateur corrigé du biais. En outre, un estimateur de l’erreur quadratique moyenne a été associé à ces estimateurs ponctuels. Sinha & Rao (2009) proposent une procédure bootstrap paramétrique pour estimer l’erreur quadratique moyenne. Des méthodes analytiques sont proposées dans Chambers et al. (2014). Cependant, leur validité théorique n’a pas été établie et leurs performances empiriques ne sont pas pleinement satisfaisantes. Ici, nous examinons deux nouvelles approches pour obtenir une version robuste du meilleur prédicteur linéaire sans biais empirique : la première est fondée sur les travaux de Chambers (1986), et la deuxième est basée sur le concept de biais conditionnel comme mesure de l’influence d’une unité de la population. Ces deux classes d’estimateurs robustes des petits domaines incluent également un terme de correction pour le biais. Cependant, ils utilisent tous les deux l’information disponible dans tous les domaines contrairement à celui de Chambers et al. (2014) qui utilise uniquement l’information disponible dans le domaine d’intérêt. Dans certaines situations, un biais non négligeable est possible pour l’estimateur de Sinha & Rao (2009), alors que les estimateurs proposés exhibent un faible biais pour un choix approprié de la fonction d’influence et de la constante de robustesse. Les simulations Monte Carlo sont effectuées, et les comparaisons sont faites entre les estimateurs proposés et ceux de Sinha & Rao (2009) et de Chambers et al. (2014). Les résultats montrent que les estimateurs de Sinha & Rao (2009) et de Chambers et al. (2014) peuvent avoir un biais important, alors que les estimateurs proposés ont une meilleure performance en termes de biais et d’erreur quadratique moyenne. En outre, nous proposons une nouvelle procédure bootstrap pour l’estimation de l’erreur quadratique moyenne des estimateurs robustes des petits domaines. Contrairement aux procédures existantes, nous montrons formellement la validité asymptotique de la méthode bootstrap proposée. Par ailleurs, la méthode proposée est semi-paramétrique, c’est-à-dire, elle n’est pas assujettie à une hypothèse sur les distributions des erreurs ou des effets aléatoires. Ainsi, elle est particulièrement attrayante et plus largement applicable. Nous examinons les performances de notre procédure bootstrap avec les simulations Monte Carlo. Les résultats montrent que notre procédure performe bien et surtout performe mieux que tous les compétiteurs étudiés. Une application de la méthode proposée est illustrée en analysant les données réelles contenant des valeurs aberrantes de Battese, Harter & Fuller (1988). S’agissant de l’imputation en présence de non-réponse partielle, certaines formes d’imputation simple ont été étudiées. L’imputation par la régression déterministe entre les classes, qui inclut l’imputation par le ratio et l’imputation par la moyenne sont souvent utilisées dans les enquêtes. Ces méthodes d’imputation peuvent conduire à des estimateurs imputés biaisés si le modèle d’imputation ou le modèle de non-réponse n’est pas correctement spécifié. Des estimateurs doublement robustes ont été développés dans les années récentes. Ces estimateurs sont sans biais si l’un au moins des modèles d’imputation ou de non-réponse est bien spécifié. Cependant, en présence des valeurs aberrantes, les estimateurs imputés doublement robustes peuvent être très instables. En utilisant le concept de biais conditionnel, nous proposons une version robuste aux valeurs aberrantes de l’estimateur doublement robuste. Les résultats des études par simulations montrent que l’estimateur proposé performe bien pour un choix approprié de la constante de robustesse.

Sampling, WLS, and Mixed Models

Mixed models may be defined with or without reference to sampling, and can be used to predict realized random effects, as when estimating the latent values of study subjects measured with response error. When the model is specified without reference to sampling, a simple mixed model includes two random variables, one stemming from an exchangeable distribution of latent values of study subjects and the other, from the study subjects` response error distributions. Positive probabilities are assigned to both potentially realizable responses and artificial responses that are not potentially realizable, resulting in artificial latent values. In contrast, finite population mixed models represent the two-stage process of sampling subjects and measuring their responses, where positive probabilities are only assigned to potentially realizable responses. A comparison of the estimators over the same potentially realizable responses indicates that the optimal linear mixed model estimator (the usual best linear unbiased predictor, BLUP) is often (but not always) more accurate than the comparable finite population mixed model estimator (the FPMM BLUP). We examine a simple example and provide the basis for a broader discussion of the role of conditioning, sampling, and model assumptions in developing inference.

Predicting random effects with an expanded finite population mixed model

Prediction of random effects is an important problem with expanding applications. In the simplest context, the problem corresponds to prediction of the latent value (the mean) of a realized cluster selected via two-stage sampling. Recently, Stanek and Singer [Predicting random effects from finite population clustered samples with response error. J. Amer. Statist. Assoc. 99, 119-130] developed best linear unbiased predictors (BLUP) under a finite population mixed model that outperform BLUPs from mixed models and superpopulation models. Their setup, however, does not allow for unequally sized clusters. To overcome this drawback, we consider an expanded finite population mixed model based on a larger set of random variables that span a higher dimensional space than those typically applied to such problems. We show that BLUPs for linear combinations of the realized cluster means derived under such a model have considerably smaller mean squared error (MSE) than those obtained from mixed models, superpopulation models, and finite population mixed models. We motivate our general approach by an example developed for two-stage cluster sampling and show that it faithfully captures the stochastic aspects of sampling in the problem. We also consider simulation studies to illustrate the increased accuracy of the BLUP obtained under the expanded finite population mixed model. (C) 2007 Elsevier B.V. All rights reserved.

Selection of alfalfa cultivars adapted for tropical environments with repeated measures using PROC MIXED of SAS (R) System

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Prediction with measurement errors in finite populations

We address the problem of selecting the best linear unbiased predictor (BLUP) of the latent value (e.g., serum glucose fasting level) of sample subjects with heteroskedastic measurement errors. Using a simple example, we compare the usual mixed model BLUP to a similar predictor based on a mixed model framed in a finite population (FPMM) setup with two sources of variability, the first of which corresponds to simple random sampling and the second, to heteroskedastic measurement errors. Under this last approach, we show that when measurement errors are subject-specific, the BLUP shrinkage constants are based on a pooled measurement error variance as opposed to the individual ones generally considered for the usual mixed model BLUP. In contrast, when the heteroskedastic measurement errors are measurement condition-specific, the FPMM BLUP involves different shrinkage constants. We also show that in this setup, when measurement errors are subject-specific, the usual mixed model predictor is biased but has a smaller mean squared error than the FPMM BLUP which points to some difficulties in the interpretation of such predictors. (C) 2011 Elsevier By. All rights reserved.

The accuracy of varietal selection using factor analytic models for multi-environment plant breeding trials

Modeling of cultivar x trial effects for multienvironment trials (METs) within a mixed model framework is now common practice in many plant breeding programs. The factor analytic (FA) model is a parsimonious form used to approximate the fully unstructured form of the genetic variance-covariance matrix in the model for MET data. In this study, we demonstrate that the FA model is generally the model of best fit across a range of data sets taken from early generation trials in a breeding program. In addition, we demonstrate the superiority of the FA model in achieving the most common aim of METs, namely the selection of superior genotypes. Selection is achieved using best linear unbiased predictions (BLUPs) of cultivar effects at each environment, considered either individually or as a weighted average across environments. In practice, empirical BLUPs (E-BLUPs) of cultivar effects must be used instead of BLUPs since variance parameters in the model must be estimated rather than assumed known. While the optimal properties of minimum mean squared error of prediction (MSEP) and maximum correlation between true and predicted effects possessed by BLUPs do not hold for E-BLUPs, a simulation study shows that E-BLUPs perform well in terms of MSEP.

Finite mixture regression model with random effects: application to neonatal hospital length of stay

A two-component mixture regression model that allows simultaneously for heterogeneity and dependency among observations is proposed. By specifying random effects explicitly in the linear predictor of the mixture probability and the mixture components, parameter estimation is achieved by maximising the corresponding best linear unbiased prediction type log-likelihood. Approximate residual maximum likelihood estimates are obtained via an EM algorithm in the manner of generalised linear mixed model (GLMM). The method can be extended to a g-component mixture regression model with the component density from the exponential family, leading to the development of the class of finite mixture GLMM. For illustration, the method is applied to analyse neonatal length of stay (LOS). It is shown that identification of pertinent factors that influence hospital LOS can provide important information for health care planning and resource allocation. (C) 2002 Elsevier Science B.V. All rights reserved.

Regional differences of outpatient physician supply as a theoretical economic and empirical generalized linear model

BACKGROUND: Regional differences in physician supply can be found in many health care systems, regardless of their organizational and financial structure. A theoretical model is developed for the physicians' decision on office allocation, covering demand-side factors and a consumption time function. METHODS: To test the propositions following the theoretical model, generalized linear models were estimated to explain differences in 412 German districts. Various factors found in the literature were included to control for physicians' regional preferences. RESULTS: Evidence in favor of the first three propositions of the theoretical model could be found. Specialists show a stronger association to higher populated districts than GPs. Although indicators for regional preferences are significantly correlated with physician density, their coefficients are not as high as population density. CONCLUSIONS: If regional disparities should be addressed by political actions, the focus should be to counteract those parameters representing physicians' preferences in over- and undersupplied regions.

Hybridisation of Australian chickpea cultivars with wild Cicer spp. increases resistance to root-lesion nematodes (Pratylenchus thornei and P. neglectus).

Australian and international chickpea (Cicer arietinum) cultivars and germplasm accessions, and wild annual Cicer spp. in the primary and secondary gene pools, were assessed in glasshouse experiments for levels of resistance to the root-lesion nematodes Pratylenchus thornei and P. neglectus. Lines were grown in replicated experiments in pasteurised soil inoculated with a pure culture of either P. thornei or P. neglectus and the population density of the nematodes in the soil plus roots after 16 weeks growth was used as a measure of resistance. Combined statistical analyses of experiments (nine for P. thornei and four for P. neglectus) were conducted and genotypes were assessed using best linear unbiased predictions. Australian and international chickpea cultivars possessed a similar range of susceptibilities through to partial resistance. Wild relatives from both the primary (C. reticulatum and C. echinospermum) and secondary (C. bijugum) gene pools of chickpea were generally more resistant than commercial chickpea cultivars to either P. thornei or P. neglectus or both. Wild relatives of chickpea have probably evolved to have resistance to endemic root-lesion nematodes whereas modern chickpea cultivars constitute a narrower gene pool with respect to nematode resistance. Resistant accessions of C. reticulatum and C. echinospermum were crossed and topcrossed with desi chickpea cultivars and resistant F(4) lines were obtained. Development of commercial cultivars with the high levels of resistance to P. thornei and P. neglectus in these hybrids will be most valuable for areas of the Australian grain region and other parts of the world where alternating chickpea and wheat crops are the preferred rotation.