Extreme Value Theory versus traditional GARCH approaches applied to financial data: a comparative evaluation

Although stock prices fluctuate, the variations are relatively small and are frequently assumed to be normal distributed on a large time scale. But sometimes these fluctuations can become determinant, especially when unforeseen large drops in asset prices are observed that could result in huge losses or even in market crashes. The evidence shows that these events happen far more often than would be expected under the generalized assumption of normal distributed financial returns. Thus it is crucial to properly model the distribution tails so as to be able to predict the frequency and magnitude of extreme stock price returns. In this paper we follow the approach suggested by McNeil and Frey (2000) and combine the GARCH-type models with the Extreme Value Theory (EVT) to estimate the tails of three financial index returns DJI,FTSE 100 and NIKKEI 225 representing three important financial areas in the world. Our results indicate that EVT-based conditional quantile estimates are much more accurate than those from conventional AR-GARCH models assuming normal or Student’s t-distribution innovations when doing out-of-sample estimation (within the insample estimation, this is so for the right tail of the distribution of returns).

A comparative study of alternative approaches for common factors identification

Preliminary version

Word learning and text organisation: an intervention case

In the present study we focus on the interaction between the acquisition of new words and text organisation. In the acquisition of new words we emphasise the acquisition of paradigmatic relations such as hyponymy, meronymy and semantic sets. We work with a group of girls attending a private school for adolescents in serious difficulties. The subjects are from disadvantaged families. Their writing skills were very poor. When asked to describe a garden, they write a short text of a single paragraph, the lexical items were generic, there were no adjectives, and all of them use mainly existential verbs. The intervention plan assumed that subjects must to be exposed to new words, working out its meaning. In presence of referents subjects were taught new words making explicit the intended relation of the new term to a term already known. In the classroom subjects were asked to write all the words they knew drawing the relationships among them. They talk about the words specifying the relation making explicit pragmatic directions like is a kind of, is a part of or are all x. After that subjects were exposed to the task of choosing perspective. The work presented in this paper accounts for significant differences in the text of the subjects before and after the intervention. While working new words subjects were organising their lexicon and learning to present a whole entity in perspective.

A participação das crianças em Intervenção precoce: representações sociais das técnicas e das famílias

Dissertação apresentada à Escola Superior de Educação de Lisboa para a obtenção de grau de Mestre em Ciências da Educação Especialização em Intervenção Precoce

Early literacy development in Catalan: characteristics and instructional influence

Resumo: Este artigo analisa a relação entre o nível de consciência fonológica, conhecimento das letra e as estratégias utilizadas para ler e escrever, em crianças de cinco anos, ensinadas em catalão. Participaram 69 crianças de três classes diferentes. Cada um dos seus professores utilizava um método diferente de ensino: analítico, sintético ou analítico-sintético. As crianças foram avaliadas no início e no final do ano letivo em: Reconhecimento de letras, segmentação palavra oral, leitura de palavras, leitura de um texto curto e um ditado. Foram realizadas análises de granulação fina em nas respostas das crianças, para identificar estratégias e padrões específicos. A análise qualitativa indica que a capacidade de segmentar uma palavra em sílabas por via oral parece ser suficiente para as crianças começarem a ler de uma forma convencional. Além disso, a consciência fonológica e o conhecimento das letras são usados em formas relativamente diferentes, dependendo do tipo de texto a ser lido. As abordagens de ensino dos professores parecem ter uma influência nos resultados das crianças.

Development of TNBS-induced colitis: animal model to test new pharmacological approaches

IBD is a gastro-intestinal disorder marked with chronic inflammation of intestinal epithelium, damaging mucosal tissue and manifests into several intestinal and extra-intestinal symptoms. Currently used medical therapy is able to induce and maintain the patient in remission, however no modifies or reverses the underlying pathogenic mechanism. The research of other medical approaches is crucial to the treatment of IBD and, for this, it´s important to use animal models to mimic the characteristics of disease in real life. The aim of the study is to develop an animal model of TNBS-induced colitis to test new pharmacological approaches. TNBS was instilled intracolonic single dose as described by Morris et al. It was administered 2,5% TNBS in 50% ethanol through a catheter carefully inserted into the colon. Mice were kept in a Tredelenburg position to avoid reflux. On day 4 and 7, the animals were sacrificed by cervical dislocation. The induction was confirmed based on clinical symptoms/signs, ALP determination and histopathological analysis. At day 4, TNBS group presented a decreased body weight and an alteration of intestinal motility characterized by diarrhea, severe edema of the anus and moderate morbidity, while in the two control groups weren’t identified any alteration on the clinical symptoms/signs with an increase of the body weight. TNBS group presented the highest concentrations of ALP comparing with control groups. The histopathology analysis revealed severe necrosis of the mucosa with widespread necrosis of the intestinal glands. Severe hemorrhagic and purulent exsudates were observed in the submucosa, muscular and serosa. TNBS group presented clinical symptoms/signs and histopathological features compatible with a correct induction of UC. The peak of manifestations became maximal at day 4 after induction. This study allows concluding that it’s possible to develop a TNBS induced colitis 4 days after instillation.

Incremental filter and wrapper approaches for feature discretization

Discrete data representations are necessary, or at least convenient, in many machine learning problems. While feature selection (FS) techniques aim at finding relevant subsets of features, the goal of feature discretization (FD) is to find concise (quantized) data representations, adequate for the learning task at hand. In this paper, we propose two incremental methods for FD. The first method belongs to the filter family, in which the quality of the discretization is assessed by a (supervised or unsupervised) relevance criterion. The second method is a wrapper, where discretized features are assessed using a classifier. Both methods can be coupled with any static (unsupervised or supervised) discretization procedure and can be used to perform FS as pre-processing or post-processing stages. The proposed methods attain efficient representations suitable for binary and multi-class problems with different types of data, being competitive with existing methods. Moreover, using well-known FS methods with the features discretized by our techniques leads to better accuracy than with the features discretized by other methods or with the original features. (C) 2013 Elsevier B.V. All rights reserved.

Data analytics in the cloud with flexible mapreduced workflows

Data analytic applications are characterized by large data sets that are subject to a series of processing phases. Some of these phases are executed sequentially but others can be executed concurrently or in parallel on clusters, grids or clouds. The MapReduce programming model has been applied to process large data sets in cluster and cloud environments. For developing an application using MapReduce there is a need to install/configure/access specific frameworks such as Apache Hadoop or Elastic MapReduce in Amazon Cloud. It would be desirable to provide more flexibility in adjusting such configurations according to the application characteristics. Furthermore the composition of the multiple phases of a data analytic application requires the specification of all the phases and their orchestration. The original MapReduce model and environment lacks flexible support for such configuration and composition. Recognizing that scientific workflows have been successfully applied to modeling complex applications, this paper describes our experiments on implementing MapReduce as subworkflows in the AWARD framework (Autonomic Workflow Activities Reconfigurable and Dynamic). A text mining data analytic application is modeled as a complex workflow with multiple phases, where individual workflow nodes support MapReduce computations. As in typical MapReduce environments, the end user only needs to define the application algorithms for input data processing and for the map and reduce functions. In the paper we present experimental results when using the AWARD framework to execute MapReduce workflows deployed over multiple Amazon EC2 (Elastic Compute Cloud) instances.

Approaches to tuberculosis mucosal vaccine development using nanoparticles and microparticles: a review

Next-generation vaccines for tuberculosis should be designed to prevent the infection and to achieve sterile eradication of Mycobacterium tuberculosis. Mucosal vaccination is a needle-free vaccine strategy that provides protective immunity against pathogenic bacteria and viruses in both mucosal and systemic compartments, being a promising alternative to current tuberculosis vaccines. Micro and nanoparticles have shown great potential as delivery systems for mucosal vaccines. In this review, the immunological principles underlying mucosal vaccine development will be discussed, and the application of mucosal adjuvants and delivery systems to the enhancement of protective immune responses at mucosal surfaces will be reviewed, in particular those envisioned for oral and nasal routes of administration. An overview of the essential vaccine candidates for tuberculosis in clinical trials will be provided, with special emphasis on the potential different antigens and immunization regimens.

Robot visual localization through local feature fusion: an evaluation of multiple classifiers combination approaches

In the last decade, local image features have been widely used in robot visual localization. In order to assess image similarity, a strategy exploiting these features compares raw descriptors extracted from the current image with those in the models of places. This paper addresses the ensuing step in this process, where a combining function must be used to aggregate results and assign each place a score. Casting the problem in the multiple classifier systems framework, in this paper we compare several candidate combiners with respect to their performance in the visual localization task. For this evaluation, we selected the most popular methods in the class of non-trained combiners, namely the sum rule and product rule. A deeper insight into the potential of these combiners is provided through a discriminativity analysis involving the algebraic rules and two extensions of these methods: the threshold, as well as the weighted modifications. In addition, a voting method, previously used in robot visual localization, is assessed. Furthermore, we address the process of constructing a model of the environment by describing how the model granularity impacts upon performance. All combiners are tested on a visual localization task, carried out on a public dataset. It is experimentally demonstrated that the sum rule extensions globally achieve the best performance, confirming the general agreement on the robustness of this rule in other classification problems. The voting method, whilst competitive with the product rule in its standard form, is shown to be outperformed by its modified versions.

Text classification using compression-based dissimilarity measures

Arguably, the most difficult task in text classification is to choose an appropriate set of features that allows machine learning algorithms to provide accurate classification. Most state-of-the-art techniques for this task involve careful feature engineering and a pre-processing stage, which may be too expensive in the emerging context of massive collections of electronic texts. In this paper, we propose efficient methods for text classification based on information-theoretic dissimilarity measures, which are used to define dissimilarity-based representations. These methods dispense with any feature design or engineering, by mapping texts into a feature space using universal dissimilarity measures; in this space, classical classifiers (e.g. nearest neighbor or support vector machines) can then be used. The reported experimental evaluation of the proposed methods, on sentiment polarity analysis and authorship attribution problems, reveals that it approximates, sometimes even outperforms previous state-of-the-art techniques, despite being much simpler, in the sense that they do not require any text pre-processing or feature engineering.