• Classical extreme value index estimators are known to be quite sensitive the number k of top order statistics used in estimation. The recently developed second reduced-bias show much less sensitivity changes k. Here, we interested improvement performance based on an exponential regression model applied scaled log-spacings statistics. In achieve that improvement, estimation a “scale” and “shape” parameters bias is performed at level k1 larger than which compute estimators. This enables us...

OBJECTIVES: The aim of this work was to study the interaction between genetic polymorphisms (singlenucleotide polymorphisms, SNPs) pro- and anti-inflammatory cytokines fat intake on risk developing Crohn's disease (CD) or modifying activity. METHODS: Seven SNPs in interleukin 1 (IL1), tumor necrosis factor alpha (TNFα), lymphotoxin (LTα), IL6 genes were analyzed 116 controls 99 patients with CD. type evaluated, dietary modulating activity analyzed. RESULTS: Individuals who homozygous for...

In this article, we revisit the importance of generalized jackknife in construction reliable semi-parametric estimates some parameters extreme or even rare events. The statistic is applied to a minimum-variance reduced-bias estimator positive value index—a primary parameter statistics extremes. A couple refinements are proposed and simulation study shows that these able achieve lower mean square error. real data illustration also provided.

This paper presents a novel approach that integrates participatory methods and rapid appraisal process to identify constraints select potentially innovative solutions aimed at improving water energy use efficiency different levels in collective irrigation systems. First, set of quantitative performance indicators is calculated, allowing the identification main problems. The study then adopts bottom-up emphasizes need for active involvement stakeholders from backgrounds potential...

The field of statistical extreme value theory (EVT) focuses on estimating parameters associated with events, such as the probability exceeding a high threshold or determining quantile that lies at beyond observed data range. Typically, assumption for univariate analysis is sample complete, independent, identically distributed, weakly dependent and stationary, drawn from an unknown distribution F. However, in context lifetime data, censoring common issue. In this work, we consider case random...

A wavelet based approach is proposed in this paper for analysis and optimization of the dynamical response a multilayered medium subject to moving load with respect material properties thickness supporting half-space. The investigated model consists along beam resting on surface infinite layers different physical properties. theoretical described by Euler-Bernoulli equation Navier's elastodynamic motion viscoelastic modelled finite series distributed harmonic loads. special method expansion...

In Statistics of Extremes, the estimation parameters extreme or even rare events is usually done under a semi-parametric framework. The estimators are based on largest k-ordered statistics in sample excesses over high level u. Although showing good asymptotic properties, most those present strong dependence k u with bias when increases decreases. use resampling methodologies has revealed to be promising reduction and choice Different approaches for need considered depending whether we an...

Time series analysis deals with records that are collected over time. The objectives of time depend on the applications, but one main goals is to predict future values series. These depend, usually in a stochastic manner, observations available at present. Such dependence has be considered when predicting from its past, taking into account trend, seasonality and other features data. Some most successful forecasting methods based concept exponential smoothing. There variety fall smoothing...

In this article the authors expose an automatic procedure that combines a very popular resampling technique, Bootstrap methodology, with one of most widely used forecasting methods, exponential smoothing. The merge these two approaches originates Boot.EXPOS. algorithm can be summarized as follow: Given time series, it starts by selecting "best" EXPOS model for fitting data, using AIC criterion. fitted values and estimated parameters are kept later reconstructing series. Concerning random...