Manuela M. Oliveira

Characterization of wildfires in Portugal

Forest fires severity has increased in Portugal in the last decades. Climate change scenarios suggest the reinforcement of this severity. Forest ecosystem managers and policy-makers thus face the challenge of developing effective fire prevention policies. The characterization of forest fires is instrumental for meeting this challenge. An approach for characterizing fire occurrence in Portugal, combining the use of geographic information systems and statistical analysis techniques, is presented. Emphasis was on the relationships between ecological and socioeconomic features and fire occurrence. The number and sizes of wildfires in Portugal were assessed for three 5-year periods (1987–1991, 1990–1994, and 2000–2004). Features maps were overlaid with perimeters of forest fires, and the proportion of burned area for each period was modeled using weighted generalized linear models (WGLM). Descriptive statistics showed variations in the distribution of fire size over recent decades, with a significant increase in the number of very large fires. Modeling underlined the impact of the forest cover type on the proportion of area burned. The statistical analysis further showed that socioeconomic features such as the proximity to roads impact the probability of fires occurrence. Results suggest that this approach may provide insight needed to develop fire prevention policies.

Modelling series of studies with a common structure

Consider the situation where the Structuration des Tableaux a Trois Indices de la Statistique (STATIS) methodology is applied to a series of studies, each study being represented by data and weight matrices. Relations between studies may be captured by the Hilbert-Schmidt product of these matrices. Specifically, the eigenvalues and eigenvectors of the Hilbert-Schmidt matrix S may be used to obtain a geometrical representation of the studies. The studies in a series may further be considered to have a common structure whenever their corresponding points lie along the first axis. The matrix S can be expressed as the sum of a rank 1 matrix @luu^T with an error matrix E. Therefore, the components of the vector @lu are sufficient to locate the points associated to the studies. Former models for S where vec(E) are mathematically tractable and yet do not take into account the symmetry of the matrix S. Thus a new symmetric model is proposed as well as the corresponding tests for a common structure. It is further shown how to assess the goodness of fit of such models. An application to the human immunodeficiency virus (HIV) infection is used for assessing the proposed model.

AIDS in Portugal: endemic versus epidemic forecasting scenarios for mortality

Abstract Both epidemic and endemic scenarios have been proposed to study the evolution of acquired immune deficiency syndrome (AIDS) in Portugal. This article presents a multistage model to study AIDS in which the stage of infected patients precedes the stage of death by AIDS. The STATIS methodology (Structuration des Tableaux a Trois Indices de la Statistique) is used to condensate the information for these two stages. The results for the stage of infection enabled the choice of time dependent control variables for prediction of the number of deaths and the assessment of the effectiveness of anti-retro-virus treatments. These predictions point towards endemic scenarios and to anti-retro virus treatments effectiveness lower than in other European countries. Moreover, when both series are jointly considered, the results obtained point to a lag of 2 to 3 years between infection by AIDS and death by connected causes. The multistage approach is more centered on actual data than other approaches (e.g. back-projection).

One-way random effects ANOVA: An extension to samples with random size

The aim of this paper is to extend one-way random effects ANOVA to situations in which we can not previously know the sample sizes. In this case it is more appropriate to consider the sample sizes as realizations of random variables. We will obtain the distribution of the F-tests, which has random degrees of freedom for the errors. Moreover we will show the equivalence between two expressions for the F-tests.

Wild Carrot Differentiation in Europe and Selection at DcAOX1 Gene

By definition, the domestication process leads to an overall reduction of crop genetic diversity. This lead to the current search of genomic regions in wild crop relatives (CWR), an important task for modern carrot breeding. Nowadays massive sequencing possibilities can allow for discovery of novel genetic resources in wild populations, but this quest could be aided by the use of a surrogate gene (to first identify and prioritize novel wild populations for increased sequencing effort). Alternative oxidase (AOX) gene family seems to be linked to all kinds of abiotic and biotic stress reactions in various organisms and thus have the potential to be used in the identification of CWR hotspots of environment-adapted diversity. High variability of DcAOX1 was found in populations of wild carrot sampled across a West-European environmental gradient. Even though no direct relation was found with the analyzed climatic conditions or with physical distance, population differentiation exists and results mainly from the polymorphisms associated with DcAOX1 exon 1 and intron 1. The relatively high number of amino acid changes and the identification of several unusually variable positions (through a likelihood ratio test), suggests that DcAOX1 gene might be under positive selection. However, if positive selection is considered, it only acts on some specific populations (i.e. is in the form of adaptive differences in different population locations) given the observed high genetic diversity. We were able to identify two populations with higher levels of differentiation which are promising as hot spots of specific functional diversity.

Estimation in Models with Commutative Orthogonal Block Structure

A model with variance-covariance matrix V = Σi=1vσi2Pi, where P1, …, Pv are known pairwise orthogonal orthogonal projection matrices, will have Orthogonal Block Structure with variance components σ12, …, σv2. Moreover, if matrices P1, …, Pv commute with the orthogonal projection matrix T on the space spanned by the mean vector, the model will have Commutative Orthogonal Block Structure (COBS). In this paper we will use Commutative Jordan Algebras to study the algebraic properties of these models as well as optimal estimators. We show that once normality is assumed, sufficient complete statistics are obtained and estimators are Uniformly Minimum Variance Unbiased Estimators.

A Bayesian Modelling of Wildfires in Portugal

In the last decade wildfires became a serious problem in Portugal due to socieconomic and climate change trends. In order to analyse wildfire data, we employ beta regression for modelling the proportion of burned wild area, under a Bayesian perspective. Our main goal is to find out fire risk factors that influence the proportion of area burned and what may make a wild area susceptible or resistant to fire. Then, we analyse wildfire data in Portugal during 1990–1994 through Bayesian normal and beta regression models that use Markov chain Monte Carlo methods for estimating quantities of interest.

Multicentric Genome-Wide Association Study for Primary Spontaneous Pneumothorax

Despite elevated incidence and recurrence rates for Primary Spontaneous Pneumothorax (PSP), little is known about its etiology, and the genetics of idiopathic PSP remains unexplored. To identify genetic variants contributing to sporadic PSP risk, we conducted the first PSP genome-wide association study. Two replicate pools of 92 Portuguese PSP cases and of 129 age- and sex-matched controls were allelotyped in triplicate on the Affymetrix Human SNP Array 6.0 arrays. Markers passing quality control were ranked by relative allele score difference between cases and controls (|RASdiff|), by a novel cluster method and by a combined Z-test. 101 single nucleotide polymorphisms (SNPs) were selected using these three approaches for technical validation by individual genotyping in the discovery dataset. 87 out of 94 successfully tested SNPs were nominally associated in the discovery dataset. Replication of the 87 technically validated SNPs was then carried out in an independent replication dataset of 100 Portuguese cases and 425 controls. The intergenic rs4733649 SNP in chromosome 8 (between LINC00824 and LINC00977) was associated with PSP in the discovery (P = 4.07E-03, ORC[95% CI] = 1.88[1.22–2.89]), replication (P = 1.50E-02, ORC[95% CI] = 1.50[1.08–2.09]) and combined datasets (P = 8.61E-05, ORC[95% CI] = 1.65[1.29–2.13]). This study identified for the first time one genetic risk factor for sporadic PSP, but future studies are warranted to further confirm this finding in other populations and uncover its functional role in PSP pathogenesis.

Application domains for the Delta method

The Delta method uses truncated Lagrange expansions of statistics to obtain approximations to their distributions. In this paper, we consider statistics Y=g(μ+X), where X is any random vector. We obtain domains 𝒟 such that, when μ∈𝒟, we may apply the distribution derived from the Delta method. Namely, we will consider an application on the normal case to illustrate our approach.

Transversal analysis in matched series of studies

In STATIS, relations between studies are throught to be captured by the Hilbert-Schmidt product of matrices associated with a series of studies. [2] showed how to obtain a geometrical representations of the studies using the eigenvalues and eigenvectors of the matrix S. In this paper we present a model and a corresponding transversal analysis. An application to elections in Portugal is presented.