In this work we introduce the class of Unit-Weibull Autoregressive Moving Average models for continuous random variables taking values in (0, 1). The proposed model is an observation driven one, for which, conditionally on a set of covariates and the process’ history, the random component is assumed to follow a Unit-Weibull distribution parameterized through its $$\rho $$th quantile. The systematic component prescribes an ARMA-like structure to model the conditional $$\rho $$th quantile by means of a link. Parameter estimation in the proposed model is performed using partial maximum likelihood, for which we provide closed formulas for the score vector and partial information matrix. We also discuss some inferential tools, such as the construction of confidence intervals, hypotheses testing, model selection, and forecasting. A Monte Carlo simulation study is conducted to assess the finite sample performance of the proposed partial maximum likelihood approach. Finally, we examine the prediction power by contrasting our method with others in the literature using the Manufacturing Capacity Utilization from the US.

O debate acerca de qual é a natureza do conteúdo da experiência perceptiva ganhou novos contornos nas últimas décadas ao se introduzir a questão de se este conteúdo é conceitual ou não conceitual. Essa questão metafísica acerca da natureza da percepção é geralmente pressionada por uma outra de índole epistêmica: como a experiência perceptiva pode justificar crenças acerca do nosso entorno? John McDowell sustenta que, se a experiência já não tem um conteúdo conceitual de modo a apresentar o mundo como sendo de uma determinada maneira, acarretando assim um elo comum entre percepção e pensamento, então é difícil ver como a experiência poderia justificar uma crença, especialmente se entendemos a justificação em termos internalistas, como faz McDowell. Contrapondo-se a essa posição, Athanassios Raftopoulos alega que se a experiência perceptiva envolve conceitos intrinsecamente e, portanto, é penetrada cognitivamente, então a experiência não é independente das nossas crenças de fundo e, desse modo, não pode funcionar como um tribunal neutro de justificação, pois o apoio evidencial fornecido pela experiência é circular e epistemologicamente viciado. Neste texto, eu defendo uma explicação de como a experiência perceptiva mantém uma relação racional com o pensamento empírico. Na primeira parte, vou elaborar duas teses que são centrais para explicar o papel de justificação da experiência perceptiva segundo uma perspectiva minimamente internalista, a saber, a tese do conteúdo comum entre a percepção e a crença e a tese da independência da percepção em relação à crença. Indicarei as dificuldades que estão envolvidas na tentativa de conciliar essas teses. A primeira parece requerer o conceitualismo de conteúdo, enquanto a segunda parece implicar sua rejeição. Apesar de declarações em contrário, eu argumento que McDowell falha em fazer justiça à segunda tese em Mind and World. Na segunda parte, apoiado na teoria enativa da percepção, de Alva Noë, defendo uma leitura menos intelectualista da primeira tese, descomprometida com o conceitualismo de conteúdo, e mostro como ela pode ser conciliada com a segunda. Finalmente, explico como atos perceptivos que nos dão acesso direto a objetos podem coagir racionalmente o pensamento empírico acerca do mundo circundante. Essa explicação pretende fazer justiça a um internalismo que qualifico como mínimo.

The present study analyzed how the economic, social and human mobility factors were responsible for dissemination of Covid -19 in Brazil and the Legal Amazon region. Human mobility was analyzed by four dimensions according to the network's hierarchies of: migration, pendular mobility, airlift, hydro and road routes and healthcare system. Manaus, capital of Amazon, was the first diffuser pole of cases; this may be explained by absence of public lockdown policies and restriction of mobility by river routes and airport system. In the face of the worsening of the pandemic, between March to May 2020, the previous migratory pattern of the urban population was accentuated to inland Amazonian cities that spread the virus towards remote areas of the Amazon. In addition, there was a pendular migratory movement to Manaus, which is the only center in the region with highly complex hospitals; this fact led to a strong migratory movement of populations seeking medical assistance. The analysis on migration revealed a close relation of the spatiotemporal behavior of Covid-19 spread and the migration network to Manaus. There were significant correlations related to fluvial or waterway transportation axis along the Amazon River which is the dominant route of the region. These pathways have long distances to be covered from one pole to another and were additional factors for the spread of the pandemic during the period studied and have long travel times that can be an important factor for COVID-19 further dissemination. We conclude that the wide dissemination of COVID-19 cases across the Legal Amazon was the result of multifactorial causes that include social inequities, vulnerability, high rate of mobility and migration, information failure and administrative and social management of the crisis.

Clustering methods are valuable tools for the identifcation of patterns in high dimensional data with applications in many scientifc felds. However, quantifying uncertainty in clustering is a challenging problem, particularly when dealing with High Dimension Low Sample Size (HDLSS) data. We develop a U-statistics based clustering approach that assesses statistical signifcance in clustering and is specifcally tailored to HDLSS scenarios. These non-parametric methods rely on very few assumptions about the data, and thus can be applied to a wide range of dataset for which the Euclidean distance captures relevant features. Our main result is the development of a hierarchical signifcance clustering method. In order to do so, we first introduce an extension of a relevant U-statistic and develop its asymptotic theory. Additionally, as a preliminary step, we propose a binary non-nested signifcance clustering method and show its optimality in terms of expected values. Our approach is tested through multiple simulations and found to have more statistical power than competing alternatives in all scenarios considered. They are further showcased in three applications ranging from genetics to image recognition problems.

n/a