Consider estimating an unknown, but structured (e.g. sparse, low-rank, etc.), signal x0 ∈ R from a vector y ∈ R of measurements of the form yi = gi(aiTx0), where the ai’s are the rows of a known measurement matrix A, and, g(·) is a (potentially unknown) nonlinear and random link-function. Such measurement functions could arise in applications where the measurement device has nonlinearities and ...

In the paper we propose nonparametric approaches for elearning data. In particular we want to supply a measure of the relative exercises importance, to estimate the acquired Knowledge for each student and finally to personalize the e-learning platform. The methodology employed is based on a comparison between nonparametric statistics for kernel density classification and parametric models such ...

We aim at proposing a Generalized Linear Model (GLM) with binary dependent variable Y , whose link function defined by the Generalized Extreme Value (GEV) distribution. We define this model as GEV regression. The goal of this paper is to overcome the drawbacks shown by the logistic regression in rare events: the probability of rare events is underestimated and the logit link is a symmetric func...

In the paper we propose nonparametric approaches for elearning data. In particular we want to supply a measure of the relative exercises importance, to estimate the acquired Knowledge for each student and finally to personalize the e-learning platform. The methodology employed is based on a comparison between nonparametric statistics for kernel density classification and parametric models such ...

In this review, we first set out the general linear model (GLM) for the non technical reader, as a tool able to do both linear regression and ANOVA within the same flexible framework. We present a short history of its development in the fMRI community, and describe some interesting examples of its early use. We offer a few warnings, as the GLM relies on assumptions that may not hold in all situ...

iv

We statistically analysed the chemical components present in waste water from mines in Galicia (NW Spain). These elements pose a risk to public health and the environment, most particularly in the event of a failure in the containment structure of a pond or dam. The statistical processing of the data, which started with an analysis of the typical contaminants present in mining ponds and dams, p...

Rural counties face unique challenges with regard to disaster vulnerability and resilience. We compared the quality of hazard mitigation plans (HMPs) completed in accordance with provisions of the Disaster Mitigation Act of 2000 from 21 urban and 36 rural counties in three southeastern states. HMPs were content analyzed to calculate a score for six principles of plan quality. Generalized linear...

Time varying correlations are often estimated with multivariate generalized autoregressive conditional heteroskedasticity (GARCH) models that are linear in squares and cross products of the data. A new class of multivariate models called dynamic conditional correlation models is proposed. These have the  exibility of univariate GARCH models coupled with parsimonious parametric models for the c...