In this paper the existence of the corner frequency value for the seismic moment distribution is investigated, analysing worldwide data. Pareto based distributions, usually considered as the most suitable to this type of data, are fitted to the most recent data, available in a global earthquake catalog. Despite the undeniable finite nature of the seismic moment data, we conclude that no corner frequency can be established considering the available data set. © 2015 AIP Publishing LLC.

In this paper we present a parsimonious approximation of a Gaussian mixture when its components share a common mean value, i.e. a scale mixture. We show that a shifted and scaled Student’s t -distribution can be approximated to this type of mixture, and use the result to develop a hypothesis test for the equality of the components mean value. A simulation study to check the quality of the approximation is also provided, together with an application to logarithmic daily returns.

The use of three-dimensional array-based testing algorithms is more efficient and accurate in some situations than other more commonly used algorithms to protocol pooled samples testing. We evaluate the advantages of using of this complex pooling schemes with only one stage in the problem of estimation of the prevalence rate of some disease. Using simulation work, we show that it does not seem to exist any advantage in using three or even higher-dimensional arrays for this type of problem.

Pooled sample tests, firstly used on the classification problem (identifying all individuals with some characteristic), may also be applied to estimate the prevalence rate. Moreover, the pooled sample methods may attain greater efficiency when applied to estimate some prevalence rate, since it is no longer necessary to perform any individual test.We develop a maximum likelihood computational algorithm for the prevalence rate estimation, and we analyze its performance.

Since Dorfman’s seminal work, research on methodologies involving pooled sample tests has increased significantly.Moreover, the use of pooled samples refers not only to the classification problem (identifying all the infected individuals in a population), but also refers to the problem of estimating the prevalence rate p, as Sobel and Elashoff stated. The use of compound tests is not restricted to hierarchical algorithms where the most common example is Dorfman’s two-stage procedure. Matrix schemes such as the square array algorithm or multidimensional matrices schemes in certain cases outperform Dorfman’s procedure. Maximum likelihood estimates are quite difficult to compute when a procedure does not classify all individuals. This paper presents two innovative methods to compute maximum likelihood estimates in both type of procedures.

We investigate Gaussian mixtures with independent components, whose parameters are numerically estimated. A decomposition of a Gaussian mixture is presented when the components have a common variance. We introduce a shifted and scaled t-Student distribution as an approximation for the distribution of Gaussian mixtures when their components have a common mean and develop a hypothesis test for testing the equality of the components means. Finally, we analyse the fitness of the approximate model to the logarithmic daily returns of the Portuguese stock index PSI-20.

Extreme rainfall events have triggered a significant number of flash floods in Madeira Island along its past and recent history. Madeira is a volcanic island where the spatial rainfall distribution is strongly affected by its rugged topography. In this thesis, annual maximum of daily rainfall data from 25 rain gauge stations located in Madeira Island were modelled by the generalised extreme value distribution. Also, the hypothesis of a Gumbel distribution was tested by two methods and the existence of a linear trend in both distributions parameters was analysed. Estimates for the 50– and 100–year return levels were also obtained. Still in an univariate context, the assumption that a distribution function belongs to the domain of attraction of an extreme value distribution for monthly maximum rainfall data was tested for the rainy season. The available data was then analysed in order to find the most suitable domain of attraction for the sampled distribution. In a different approach, a search for thresholds was also performed for daily rainfall values through a graphical analysis. In a multivariate context, a study was made on the dependence between extreme rainfall values from the considered stations based on Kendall’s τ measure. This study suggests the influence of factors such as altitude, slope orientation, distance between stations and their proximity of the sea on the spatial distribution of extreme rainfall. Groups of three pairwise associated stations were also obtained and an adjustment was made to a family of extreme value copulas involving the Marshall–Olkin family, whose parameters can be written as a function of Kendall’s τ association measures of the obtained pairs.

The dependence between variables plays a central role in multivariate extremes. In this paper, spatial dependence of Madeira Island's rainfall data is addressed within an extreme value copula approach through an analysis of maximum annual data. The impact of altitude, slope orientation, distance between rain gauge stations and distance from the stations to the sea are investigated for two different periods of time. The results obtained highlight the influence of the island's complex topography on the spatial distribution of extreme rainfall in Madeira Island.