DSpace Collection:http://hdl.handle.net/10174/11172019-07-20T10:21:29Z2019-07-20T10:21:29ZPractical use of correlation coefficients in the Social SciencesHernández, OscarAlpizar-Jara, Russellhttp://hdl.handle.net/10174/254382019-03-29T11:39:37Z2018-06-30T23:00:00ZTitle: Practical use of correlation coefficients in the Social Sciences
Authors: Hernández, Oscar; Alpizar-Jara, Russell
Editors: Sorto, M.A.; White, A.; Guyot, L.
Abstract: The Pearson correlation coefficient (r) is usually the first measure of association taught at elementary statistics courses. The usual presentation includes scatterplots, computation and interpretation of r, properties, examples, and warnings about inferring causality from high association between two variables. On this last aspect, few introductory textbooks go deeper into the criteria for establishing causation, and there is a lack of convincing examples in the area of the Social Sciences. Although some textbooks give adequate explanations, most of their examples belong to the field of Biostatistics. There is a need to incorporate convincing cases of the practical use of correlation as supporting evidence of causal relationships in the Social Sciences. We contribute with two examples that could be useful for teaching purposes.2018-06-30T23:00:00ZInference for the Evolution in Series of StudiesAreia, A.Mexia, J.Oliveira, Mariahttp://hdl.handle.net/10174/254272019-03-25T17:30:00Z2018-07-14T23:00:00ZTitle: Inference for the Evolution in Series of Studies
Authors: Areia, A.; Mexia, J.; Oliveira, Maria
Abstract: Studies will be matrix triplets (X,Dp,Dn), where the matrix X has a
row per object and a column per variable, while Dp and Dn are
weight matrices for objects and variables, respectively.
Given a series of studies (Xi,Dp,Dn),i=1,…,k, we condense the
matrix triplets into the
, and use spectral analysis
of matrix [ ] with (
) to study
the series evolution.
When we have a series of studies for each treatment of a basis
design we carry out an ANOVA-like inference to study the action
of the factors in the base design on the evolution of the series
associated to the differents treatments.2018-07-14T23:00:00ZMen's Performance in Triple Jump: an approach with Extreme Value TheoryCaeiro, F.Silva, D.Oliveira, Manuelahttp://hdl.handle.net/10174/253532019-03-03T11:56:31Z2018-11-01T00:00:00ZTitle: Men's Performance in Triple Jump: an approach with Extreme Value Theory
Authors: Caeiro, F.; Silva, D.; Oliveira, Manuela
Editors: Skiadas, Christos H.
Abstract: Emil Gumbel was the first to use extreme value models in statistics applications. In the block method an Extreme Value distribution is fitted to the sample of
block maxima obtained from non-overlapping blocks of a series of random variables.
The block length is usually long (usually chosen as one year), to assure the independence of the block maxima sample. Although this method has proved to be useful in
diversified situations, it has also been criticized since we are wasting information by using only the observed maxima from each block. To use more information about the tail of the model underlying the data, the block maxima method was more recently
extended to the r−largest order statistics method. The choice of the number r ≥ 1
of largest order statistics taken from each block must be made with careful, due to
the usual bias and variance trade-off. In this work we use the r−largest order statistical method to study the limit of men’s performance in Triple Jump event. Our results indicate a negative extreme value index and thus a finite right endpoint for the extreme value model.2018-11-01T00:00:00ZUma comparação de métodos para análise de registos de marésCarinhas, DoraInfante, Paulohttp://hdl.handle.net/10174/245662019-02-12T12:26:29Z2018-05-31T23:00:00ZTitle: Uma comparação de métodos para análise de registos de marés
Authors: Carinhas, Dora; Infante, Paulo
Abstract: O movimento regular da maré é constantemente influenciado, a um menor ou maior grau, por efeitos meteorológicos. Em certas regiões do globo, inundações costeiras intensas podem ocorrer quando há a coincidência de fenómenos meteorológicos extremos, como tempestades tropicais ou tufões, com alturas de maré astronómica elevada. As condições meteorológicas são a principal causa das diferenças entre alturas de maré previstas e observadas, fazendo-se notar com maior intensidade nos períodos de Inverno. Este trabalho tem por objetivo apresentar uma revisão das principais metodologias de modelação e previsão de marés que provaram ser bem sucedidas numa variedade de circunstâncias.
Esses métodos incluem técnicas padrão de filtragem, como por exemplo filtros de Kalman, redes neuronais artificiais e métodos de análise por wavelets. Os métodos clássicos e os mais recentes foram revistos de forma sistemática e consistente, apresentando vantagens e desvantagens.2018-05-31T23:00:00Z