{"id":1559,"date":"2024-07-12T09:48:42","date_gmt":"2024-07-12T12:48:42","guid":{"rendered":"https:\/\/www.ufrgs.br\/ppgest\/?page_id=1559"},"modified":"2025-02-12T21:23:15","modified_gmt":"2025-02-13T00:23:15","slug":"2024-2","status":"publish","type":"page","link":"https:\/\/www.ufrgs.br\/ppgest\/2024-2\/","title":{"rendered":"2024"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-page\" data-elementor-id=\"1559\" class=\"elementor elementor-1559\">\n\t\t\t\t\t\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-8a1db2a elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"8a1db2a\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-0401b14\" data-id=\"0401b14\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-beeec24 elementor-widget elementor-widget-text-editor\" data-id=\"beeec24\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.6.2 - 04-04-2022 *\/\n.elementor-widget-text-editor.elementor-drop-cap-view-stacked .elementor-drop-cap{background-color:#818a91;color:#fff}.elementor-widget-text-editor.elementor-drop-cap-view-framed .elementor-drop-cap{color:#818a91;border:3px solid;background-color:transparent}.elementor-widget-text-editor:not(.elementor-drop-cap-view-default) .elementor-drop-cap{margin-top:8px}.elementor-widget-text-editor:not(.elementor-drop-cap-view-default) .elementor-drop-cap-letter{width:1em;height:1em}.elementor-widget-text-editor .elementor-drop-cap{float:left;text-align:center;line-height:1;font-size:50px}.elementor-widget-text-editor .elementor-drop-cap-letter{display:inline-block}<\/style>\t\t\t\t<p><span class=\"collapseomatic \" id=\"id6ae5ce050e2ab\"  tabindex=\"0\" title=\"Semin\u00e1rio 16\/07\/2024.  Prof. Dr. M\u00e1rcio Valk  - PPGEst UFRGS\"    >Semin\u00e1rio 16\/07\/2024.  Prof. Dr. M\u00e1rcio Valk  &#8211; PPGEst UFRGS<\/span><div id=\"target-id6ae5ce050e2ab\" class=\"collapseomatic_content \"><\/p><p><strong>T\u00edtulo:<\/strong> Infer\u00eancia para Agrupamento<\/p><p><strong>Resumo:<\/strong> A infer\u00eancia para agrupamento ou clustering \u00e9 fundamental para descobrir a estrutura de grupos gen\u00e9ticos aos dados. M\u00e9todos de agrupamento que avaliam signific\u00e2ncia estat\u00edstica t\u00eam chamado recentemente a aten\u00e7\u00e3o devido \u00e0 sua import\u00e2ncia para a identifica\u00e7\u00e3o de padr\u00f5es em dados de alta dimens\u00e3o com aplica\u00e7\u00f5es em diversos campos cient\u00edficos. Apresentamos aqui uma abordagem baseada em U-estat\u00edsticas, especialmente adaptada para dados de alta dimens\u00e3o, que agrupamos os dados em grupos enquanto avaliamos a signific\u00e2ncia estat\u00edstica (p-valor) dessas parti\u00e7\u00f5es. Essa metodologia n\u00e3o \u00e9 param\u00e9trica e depende de poucas suposi\u00e7\u00f5es sobre os dados e, portanto, pode ser aplicada a uma ampla gama de conjuntos de dados. Neste semin\u00e1rio pretendemos apresentar o problema, divulgar alguns avan\u00e7os nessa \u00e1rea e mostrar algumas quest\u00f5es em aberto que direcionam a nossa pesquisa.<\/p><p><\/div><\/p><p><span class=\"collapseomatic \" id=\"id6ae5ce050e2e1\"  tabindex=\"0\" title=\"Semin\u00e1rio 23\/07\/2024.  Prof. Dr. Danilo Marcondes Filho  - PPGEst UFRGS\"    >Semin\u00e1rio 23\/07\/2024.  Prof. Dr. Danilo Marcondes Filho  &#8211; PPGEst UFRGS<\/span><div id=\"target-id6ae5ce050e2e1\" class=\"collapseomatic_content \"><\/p><p><strong>T\u00edtulo:<\/strong> Multivariate Time Series Cluestering using U-Statistic-based method: An Approch for Batch Process Monitoring<\/p><p><strong>Resumo:<\/strong> Time series clustering is a consolidated research area. One of the important applications of time series clustering methods is fault detection. Following this aim, this paper presents a preliminary study about the clusterization of multivariate time series in the field of Statistical Process Control (SPC). In particular, we are focused on batch processes, a peculiar process that generates multivariate time series data for each batch sample. Here we extend a study of Cintra et al. (2023), which proposed a control approach based on U-Statistic theory focused on univariate time series. They present an approach to evaluate new batch samples by measuring U-statistics-based distances between Autocorrelation Functions (ACF) of reference and new batches, one variable at a time. This work describes an approach to evaluate batches considering additionally the cross-correlation between variables in each multivariate time series. The control charts considering the Cross-Correlation Function (CCF) and ACF of each variable jointly are built to evaluate a new batch. Through preliminary simulations, our method signalizes changes in the process affecting its dynamics, considering both serial and cross-correlation.<\/p><p><\/div><\/p><p><span class=\"collapseomatic \" id=\"id6ae5ce050e31f\"  tabindex=\"0\" title=\"Semin\u00e1rio 30\/07\/24 - Prof. Dr. Fl\u00e1vio A. Ziegelmann\"    >Semin\u00e1rio 30\/07\/24 &#8211; Prof. Dr. Fl\u00e1vio A. Ziegelmann<\/span><div id=\"target-id6ae5ce050e31f\" class=\"collapseomatic_content \"><\/p><p><strong>T\u00edtulo:\u00a0<\/strong>Dynamic Factor Copulas for Minimum-CVaR Portfolio Optimization<\/p><p><strong>Resumo:\u00a0<\/strong>Copula models have become popular for minimum conditional value-at-risk (CVaR) portfolio optimization, especially due to their ability to deal with nonlinear dependencies. Nevertheless, as the number of assets in a portfolio increases, the estimation of copulas, particularly dynamic ones, becomes computationally burdensome. In this work, our novel contribution is to adapt and implement a dynamic factor copula model for the asset returns dependencies and find an optimal, potentially high dimensional, portfolio via minimizing its CVaR. The resulting model is capable of addressing the \u201ccurse of dimensionality\u201d for the dependencies, while maintaining enough complexity and flexibility. The factor copula dynamics are described by a generalized autorregressive scores (GAS) model for the factor loadings. Using data consisting of B3 Brazilian stocks from January 2013 to December 2020, we find the optimal portfolio and evaluate its out of sample economic performance. Empirical results suggest that our min-CVaR-factor-copula strategy has either equal or better risk\/return metrics when compared to a traditional gaussian copula, while being considerably superior than both Markowitz mean-variance and equal weights portfolios as well as the IBRX50 index.<\/p><p><\/div><\/p><p><span class=\"collapseomatic \" id=\"id6ae5ce050e336\"  tabindex=\"0\" title=\"Semin\u00e1rio 06\/08\/24 - Profa. Dra. Silvana Schneider\"    >Semin\u00e1rio 06\/08\/24 &#8211; Profa. Dra. Silvana Schneider<\/span><div id=\"target-id6ae5ce050e336\" class=\"collapseomatic_content \"><\/p><p><strong>T\u00edtulo:<\/strong> Modelos de fra\u00e7\u00e3o de cura com censura dependente<\/p><p><strong>Resumo:<\/strong> Neste trabalho, propomos uma abordagem baseada em modelos de fra\u00e7\u00e3o de cura com censura dependente. A associa\u00e7\u00e3o entre tempos de falha e censura dependente \u00e9 acomodada atrav\u00e9s do modelo de fragilidade. As distribui\u00e7\u00f5es marginais s\u00e3o ajustadas pelas distribui\u00e7\u00f5es Weibull e exponencial por partes (EP). Tamb\u00e9m desenvolvemos um algoritmo EM Monte Carlo para realizar a estima\u00e7\u00e3o. Os resultados do estudo de simula\u00e7\u00e3o mostram um vi\u00e9s relativo pequeno e probabilidade de cobertura pr\u00f3xima ao valor nominal. Por fim, com o objetivo de avaliar a din\u00e2mica de vida dos c\u00e3es de rua, levando em considera\u00e7\u00e3o todas as caracter\u00edsticas dos dados, analisamos os tempos de sobreviv\u00eancia de c\u00e3es de rua da \u00cdndia.<\/p><p><\/div><\/p><p><span class=\"collapseomatic \" id=\"id6ae5ce050e344\"  tabindex=\"0\" title=\"Semin\u00e1rio 13\/08\/24 - Prof. Dr. Cleiton Guollo Taufemback\"    >Semin\u00e1rio 13\/08\/24 &#8211; Prof. Dr. Cleiton Guollo Taufemback<\/span><div id=\"target-id6ae5ce050e344\" class=\"collapseomatic_content \"><\/p><p><strong>T\u00edtulo:<\/strong> Testing for short-and long-run causality with MIDAS models<\/p><p><strong>Resumo: <\/strong>This paper proposes a Granger-causality test for mixed-frequency datasets in the frequency domain. Employing MIDAS models, we assume that the low-frequency variable is generated by its past values and the aggregation of high-frequency exogenous variables, addressing the spurious effects of temporal aggregation on causality measurements. Additionally, we employ a Maximum Monte Carlo test to address the well-known nuisance problem in MIDAS models. Our finite sample experiments demonstrate that the proposed method exhibits good size and power. Finally, we conduct an empirical study that presents a causality analysis between US quarterly GDP and monthly Consumer Price Index and Crude Oil prices.<strong><br \/><\/strong><\/p><p><\/div><\/p><p><span class=\"collapseomatic \" id=\"id6ae5ce050e351\"  tabindex=\"0\" title=\"Semin\u00e1rio 20\/08\/2024 - Profa. Dra. Taiane Schaedler Pass\"    >Semin\u00e1rio 20\/08\/2024 &#8211; Profa. Dra. Taiane Schaedler Pass<\/span><div id=\"target-id6ae5ce050e351\" class=\"collapseomatic_content \"><\/p><p><strong>T\u00edtulo: <\/strong>Modelos de regress\u00e3o para s\u00e9ries temporais limitadas e os pacotes BTSR e PTSR<\/p><p><strong>Resumo:\u00a0<\/strong>Neste semin\u00e1rio discutimos a modelagem de s\u00e9ries temporais limitadas. Em particular, discutiremos as classes de modelos implementados nos pacotes BTSR (bounded time series regression) e PTSR (positive time series regression) do software R. Apresentaremos a ideia por tr\u00e1s de tais modelos e a rela\u00e7\u00e3o dos mesmos com os modelos cl\u00e1ssicos da classe ARMA e GLM. Abordaremos tanto os aspectos te\u00f3ricos dos modelos (defini\u00e7\u00e3o, propriedades, estima\u00e7\u00e3o e previs\u00e3o) quanto os desafios computacionais de implementa\u00e7\u00e3o e utiliza\u00e7\u00e3o dos mesmos.<\/p><p><\/div><\/p><p><span class=\"collapseomatic \" id=\"id6ae5ce050e35d\"  tabindex=\"0\" title=\"Semin\u00e1rio 27\/08\/2024 - Profa. Dra. M\u00e1rcia Barbian\"    >Semin\u00e1rio 27\/08\/2024 &#8211; Profa. Dra. M\u00e1rcia Barbian<\/span><div id=\"target-id6ae5ce050e35d\" class=\"collapseomatic_content \"><\/p><p><strong>T\u00edtulo:<\/strong> Predi\u00e7\u00e3o do N\u00famero de Alunos por Munic\u00edpio do Projeto Sa\u00fade com Agente Utilizando Redes Neurais de Grafos<\/p><p><strong>Resumo:\u00a0<\/strong><span data-sheets-root=\"1\">A previs\u00e3o de dados espaciais tem ganhado crescente import\u00e2ncia em diversas \u00e1reas do conhecimento. Nesse contexto, modelos baseados em redes neurais e aprendizado profundo emergem como op\u00e7\u00f5es vi\u00e1veis para realizar tais previs\u00f5es. Destaca-se o papel das redes neurais de grafos (GNN), as quais capturam depend\u00eancia espacial presente nos dados. Isso ocorre por meio da agrega\u00e7\u00e3o realizada entre regi\u00f5es vizinhas. O foco deste trabalho envolveu a explora\u00e7\u00e3o de diferentes configura\u00e7\u00f5es de GNNs aplicadas a dados espaciais de \u00e1rea, com o objetivo de predizer o n\u00famero de alunos do projeto \u201cSa\u00fade com Agente\u201d por munic\u00edpio, considerando informa\u00e7\u00f5es demogr\u00e1ficas espec\u00edficas. Os resultados indicaram desempenho superior dos modelos que utilizam GNN em compara\u00e7\u00e3o ao MLP (Rede Neural de Multicamadas) que considera as observa\u00e7\u00f5es independentes. Al\u00e9m disso, observou-se uma melhoria na qualidade de predi\u00e7\u00e3o quando camadas lineares foram adicionadas ao modelo GraphConv.<\/span><\/p><p><\/div><\/p><p><span class=\"collapseomatic \" id=\"id6ae5ce050e369\"  tabindex=\"0\" title=\"Semin\u00e1rio 03\/09\/2024 - Prof. Dr. Eduardo de Oliveira Horta\"    >Semin\u00e1rio 03\/09\/2024 &#8211; Prof. Dr. Eduardo de Oliveira Horta<\/span><div id=\"target-id6ae5ce050e369\" class=\"collapseomatic_content \"><\/p><p><strong>T\u00edtulo:<\/strong> Product Disintegrations of Markov Chains<\/p><p><strong>Resumo:\u00a0<\/strong><span data-sheets-root=\"1\">Borsato, Horta and Souza (2024, Statistics and Probability Letters) introduced the concept of product disintegrations, a sequence of latent random measures that yield an independent sequence of observables upon conditioning. In this ongoing research, we show (constructively) that, under mild conditions, every discrete-time Markov Chain on a countable state space admits a non-trivial product disintegration. Moreover, this disintegration turns out to be also Markovian. This has implications on the pervasiveness of the Hidden Markov Model.<\/span><\/p><p><\/div><\/p><p><span class=\"collapseomatic \" id=\"id6ae5ce050e374\"  tabindex=\"0\" title=\"Semin\u00e1rio 10\/09\/2024 - Prof. Dr. Guilherme Pumi\"    >Semin\u00e1rio 10\/09\/2024 &#8211; Prof. Dr. Guilherme Pumi<\/span><div id=\"target-id6ae5ce050e374\" class=\"collapseomatic_content \"><\/p><p><strong>T\u00edtulo:<\/strong> S\u00e9ries temporais com dados faltantes &#8211; imputar ou n\u00e3o imputar?<\/p><p><strong>Resumo:\u00a0<\/strong><span data-sheets-root=\"1\">Dados faltantes em s\u00e9ries temporais \u00e9 um problema bastante comum nas mais variadas \u00e1reas. Quando o foco \u00e9 a estima\u00e7\u00e3o de algum par\u00e2metro de interesse, tipicamente podemos abordar o problema de duas maneiras: os dados faltantes podem ser imputados usando algum m\u00e9todo plaus\u00edvel e ent\u00e3o procedemos com a estimativa como se nenhum dado estivesse faltando; ou podemos aplicar uma metodologia especialmente adaptada para estimar o par\u00e2metro de interesse na presen\u00e7a de dados faltantes. Neste trabalho discutiremos os aspectos mais importantes de cada abordagem e suas vantagens e desvantagens em contextos bastante amplos. Em seguida discutiremos algumas implica\u00e7\u00f5es no contexto de modelos para s\u00e9ries temporais com longa depend\u00eancia e modelos para s\u00e9ries temporais limitadas.<\/span><\/p><p><\/div><\/p><p><span class=\"collapseomatic \" id=\"id6ae5ce050e380\"  tabindex=\"0\" title=\"Semin\u00e1rios 17\/09\/2024 - Discentes\"    >Semin\u00e1rios 17\/09\/2024 &#8211; Discentes<\/span><div id=\"target-id6ae5ce050e380\" class=\"collapseomatic_content \"><\/p><p><strong>Palestrantes:<\/strong><\/p><ol><li>Danilo Matsuoka &#8211; &#8220;A three-step approach to production frontier estimation and the Matsuoka&#8217;s distribution.&#8221;<\/li><li>Fernando Jose Monteiro de Araujo &#8211; &#8220;New generalized autoregressive score models: Forecasting sustainable development indicators&#8221;<\/li><li>Lucas Pasqualin Cantu &#8211; &#8220;Podemos colar s\u00e9ries temporais?&#8221;<\/li><\/ol><p><\/div><\/p><p><span class=\"collapseomatic \" id=\"id6ae5ce050e38a\"  tabindex=\"0\" title=\"Semin\u00e1rios 24\/09\/2024 - Discentes\"    >Semin\u00e1rios 24\/09\/2024 &#8211; Discentes<\/span><div id=\"target-id6ae5ce050e38a\" class=\"collapseomatic_content \"><\/p><p><strong>Palestrantes:<\/strong><\/p><ol><li>Douglas Krauthein Verdun &#8211; &#8220;M\u00faltipla imputa\u00e7\u00e3o de dados faltantes em s\u00e9ries temporais limitadas&#8221;<\/li><li>Tain\u00e1 Ferreira Cabalheiro &#8211; &#8220;Modelagem de t\u00f3picos em dados de texto usando BERT e m\u00e9todos de agrupamento&#8221;<\/li><li>Celso Menoti da Silva &#8211; &#8220;Modelagem da censura dependente via c\u00f3pula gaussiana e distribui\u00e7\u00e3o defeituosa&#8221;<\/li><\/ol><p><\/div><\/p><p><span class=\"collapseomatic \" id=\"id6ae5ce050e396\"  tabindex=\"0\" title=\"Semin\u00e1rio 15\/10\/2024 - Prof. Dr. Emmanuel Guerre\"    >Semin\u00e1rio 15\/10\/2024 &#8211; Prof. Dr. Emmanuel Guerre<\/span><div id=\"target-id6ae5ce050e396\" class=\"collapseomatic_content \"><\/p><p><strong>T\u00edtulo:<\/strong> Estimation under shape constraints with log barrier penalty<\/p><p><strong>Resumo:\u00a0<\/strong>This is work in progress with Nianqing Liu (Xiamen), Mohamed Merabtine (QMUL) and Quang Vuong (NYU).A common belief is that imposing inequality constraints only improves estimation when the true parameter lies near the boundary. Indeed, when the true parameter is in the interior of the constraints, the constrained and unconstrained estimators are equivalent at any order. A popular method for estimation under shape constraint employs log barrier penalty, which maximises an objective function penalised with a log barrier constraining estimation. Classical numerical approaches reestimate the parameters decreasing the weight parameter until a convergence criterion is reached. We adopt a statistical interpretation of the penalty weight , which shrinks estimation towards the constraints. Under certain circumstances, the penalty weight can be chosen optimally minimising a Mean Squared Error criterion when the true parameter lies inside the constraints. The statistically optimised constrained estimator improves on the unconstrained and constrained estimators with a magnitude which is proportional to the distance to the constraints and a vanishing power of the sample size<\/p><p><\/div><\/p><p><span class=\"collapseomatic \" id=\"id6ae5ce050e3be\"  tabindex=\"0\" title=\"Semin\u00e1rio 22\/10\/2024 - Profa. Dra. Rosangela Helena Loschi (UFMG)\"    >Semin\u00e1rio 22\/10\/2024 &#8211; Profa. Dra. Rosangela Helena Loschi (UFMG)<\/span><div id=\"target-id6ae5ce050e3be\" class=\"collapseomatic_content \"><\/p><p><strong>T\u00edtulo:<\/strong> RENeGe(Randomly Edge-Weighted Neighborhood Graphs): A new approach for spatial data<\/p><p><strong>Resumo:\u00a0<\/strong>Traditional models for areal data assume a hierarchical structure where one of the components is the random effects that spatially correlate the areas. The conditional autoregressive (CAR) model is the most popular distribution to jointly model the prior uncertainty about these spatial random effects. One limitation of the CAR distribution is the inability of producing high correlations between neighboring areas. We propose a new model for areal data that alleviates this problem. We represent the map by an undirected graph where the nodes are the areas and randomly-weighted edges connect nodes that are neighbors. The model is based on a multivariate Student-$t$ distribution, spatially structured, in which the precision matrix is indirectly built assuming a multivariate distribution for the random edges effects. The edges effects\u2019 joint distribution is a spatial multivariate Student-$t$ that induces another $t$ distribution for the areas\u2019 spatial effects which inherit its capacity to accommodate outliers and heavy-tail behavior. Most important, it can produce a higher marginal correlation between the spatial effects than the CAR model overcoming one of the main limitations to this model. We fit the proposed model to analyze real cancer maps and compared its performance with several state-of-art competitors. Our proposed model provides better fitting in almost all cases. Joint work with Danna L. Cruz and Renato M. Assun\u00e7\u00e3o. This work was supported by CAPES, CNPq and FAPEMIG.<\/p><p><\/div><\/p><p><span class=\"collapseomatic \" id=\"id6ae5ce050e3cb\"  tabindex=\"0\" title=\"Semin\u00e1rio 05\/11\/2024 - Prof. Dr. Rodney Fonseca (UFBA)\"    >Semin\u00e1rio 05\/11\/2024 &#8211; Prof. Dr. Rodney Fonseca (UFBA)<\/span><div id=\"target-id6ae5ce050e3cb\" class=\"collapseomatic_content \"><\/p><p><strong>T\u00edtulo:<\/strong> Wavelet Feature Screening<\/p><p><strong>Resumo:\u00a0<\/strong>An initial screening of which covariates are relevant is a common practice in high-dimensional regression models. The classic feature screening selects only a subset of covariates correlated with the response variable. However, many important features might have a relevant albeit highly nonlinear relation with the response. One screening approach that handles nonlinearity is to compute the correlation between the response and nonparametric functions of each covariate. Wavelets are powerful tools for nonparametric and functional data analysis but are still seldom used in the feature screening literature. In this talk, we introduce a wavelet feature screening method that can be easily implemented. Theoretical and simulation results show that the proposed method can capture true covariates with high probability, even in highly nonlinear models. We also present an example with real data in a high-dimensional setting. Joint work with Pedro Morettin and Alu\u00edsio Pinheiro.<\/p><p><\/div><\/p><p><span class=\"collapseomatic \" id=\"id6ae5ce050e3d9\"  tabindex=\"0\" title=\"Semin\u00e1rio 12\/11\/2024 - Prof. Dr. Gilney F. Zebende (UFS)\"    >Semin\u00e1rio 12\/11\/2024 &#8211; Prof. Dr. Gilney F. Zebende (UFS)<\/span><div id=\"target-id6ae5ce050e3d9\" class=\"collapseomatic_content \"><\/p><p><strong>T\u00edtulo:<\/strong> Sistemas Complexos: Autocorrela\u00e7\u00e3o e Correla\u00e7\u00f5es Cruzadas (Teoria e Aplica\u00e7\u00f5es)<\/p><p><strong>Resumo:\u00a0<\/strong>Neste semin\u00e1rio, faremos uma caminhada por ideias introduzidas por Hurst (hidrologista), Peng\/Stanley e Zebende no que tange o estudo de sistemas complexos. Aqui daremos \u00eanfase a an\u00e1lise estat\u00edstica de autocorrela\u00e7\u00e3o e correla\u00e7\u00e3o cruzada, aplicadas aos sistemas Complexos.<\/p><p><\/div><\/p><p><span class=\"collapseomatic \" id=\"id6ae5ce050e3e4\"  tabindex=\"0\" title=\"Semin\u00e1rio 19\/11\/2024 - Profa. Dra. Bruna Palm Blekinge Institute of Technology - Sueden\"    >Semin\u00e1rio 19\/11\/2024 &#8211; Profa. Dra. Bruna Palm Blekinge Institute of Technology &#8211; Sueden<\/span><div id=\"target-id6ae5ce050e3e4\" class=\"collapseomatic_content \"><\/p><p><strong>T\u00edtulo:<\/strong> Rayleigh Regression Model for Ground Type Detection in SAR Imagery<\/p><p><strong>Resumo:\u00a0<\/strong>This study proposes a regression model for nonnegative signals. The proposed regression estimates the mean of Rayleigh distributed signals by a structure that includes a set of regressors and a link function. For the proposed model, we present: (i) parameter estimation; (ii) large data record results; and (iii) a detection technique. We present closed-form expressions for the score vector and Fisher information matrix. The proposed model is submitted to extensive Monte Carlo simulations and measured data. The Monte Carlo simulations are used to evaluate the performance of maximum likelihood estimators. Also, an application compares the proposed model\u2019s detection results with Gaussian-, Gamma-, and Weibull based regression models in SAR images.<\/p><p><\/div><\/p><p><span class=\"collapseomatic \" id=\"id6ae5ce050e3f0\"  tabindex=\"0\" title=\"26\/11\/2024 - Profa. Dra. Qin Fang (University of Sydney)\"    >26\/11\/2024 &#8211; Profa. Dra. Qin Fang (University of Sydney)<\/span><div id=\"target-id6ae5ce050e3f0\" class=\"collapseomatic_content \"><\/p><p><strong>T\u00edtulo:<\/strong> On the Modelling and Prediction of High-Dimensional Functional Time Series<\/p><p><strong>Resumo:\u00a0<\/strong>We propose a two-step procedure to model and predict high-dimensional functional time series, where the number of function-valued time series $p$ is large in relation to the length of time series $n$. Our first step performs an eigenanalysis of a positive definite matrix, which leads to a one-to-one linear transformation for the original high-dimensional functional time series, and the transformed curve series can be segmented into several groups such that any two subseries from any two different groups are uncorrelated both contemporaneously and serially. Consequently in our second step those groups are handled separately without the information loss on the overall linear dynamic structure. The second step is devoted to establishing a finite-dimensional dynamical structure for all the transformed functional time series within each group. Furthermore the finite-dimensional structure is represented by that of a vector time series. Modelling and forecasting for the original high-dimensional functional time series are realized via those for the vector time series in all the groups. We investigate the theoretical properties of our proposed methods, and illustrate the finite-sample performance through both extensive simulation and two real datasets.<\/p><p><\/div><\/p><p><span class=\"collapseomatic \" id=\"id6ae5ce050e3fe\"  tabindex=\"0\" title=\"Semin\u00e1rio 03\/12\/2024 - Profa. Dra. Renata Rojas Guerra\"    >Semin\u00e1rio 03\/12\/2024 &#8211; Profa. Dra. Renata Rojas Guerra<\/span><div id=\"target-id6ae5ce050e3fe\" class=\"collapseomatic_content \"><\/p><p><strong>T\u00edtulo:<\/strong> Modelo Rayleigh de escore autorregressivo generalizado para interpreta\u00e7\u00e3o de dados de radar de abertura sint\u00e9tica<\/p><p><strong>Resumo:\u00a0<\/strong>Este trabalho introduz o modelo Rayleigh de escore autorregressivo generalizado (Ray-GAS), um modelo din\u00e2mico \u00fatil para a interpreta\u00e7\u00e3o de dados de radar de abertura sint\u00e9tica (SAR). Ele \u00e9 derivado da estrutura de escore autorregressivo generalizado (GAS), assumindo que a m\u00e9dia condicional da distribui\u00e7\u00e3o Rayleigh \u00e9 um par\u00e2metro que varia conforme o \u00edndice da imagem. S\u00e3o desenvolvidas ferramentas de estima\u00e7\u00e3o, diagn\u00f3stico e previs\u00e3o para o novo modelo. Al\u00e9m disso, realizamos experimentos num\u00e9ricos com dados simulados de amplitude de uma imagem SAR single-look para dados de regi\u00f5es de floresta e lago. Os resultados ilustram a utilidade do modelo Ray-GAS para a compreens\u00e3o do comportamento estoc\u00e1stico e para a filtragem de retornos de amplitude SAR. Este \u00e9 um trabalho conjunto com Miguel R. Pe\u00f1a-Ram\u00edrez e F\u00e1bio M. Bayer.<\/p><p><\/div><\/p><p><span class=\"collapseomatic \" id=\"id6ae5ce050e409\"  tabindex=\"0\" title=\"Semin\u00e1rio 10\/12\/2024 - Prof. Dr. Rafael Izbicki (UFSCar)\"    >Semin\u00e1rio 10\/12\/2024 &#8211; Prof. Dr. Rafael Izbicki (UFSCar)<\/span><div id=\"target-id6ae5ce050e409\" class=\"collapseomatic_content \"><\/p><p><strong>T\u00edtulo:<\/strong> Local Prediction Sets With Applications to Statistical Inference<\/p><p><strong>Resumo:\u00a0<\/strong>Quantifying uncertainty is essential for reliable predictive modeling and statistical inference. Traditional conformal methods ensure marginally valid prediction intervals but often lack adaptability and fail to achieve conditional coverage. We introduce a model-agnostic approach leveraging regression trees and Random Forests to construct data-adaptive partitions that approximate local coverage guarantees, enhancing scalability and accuracy of existing approaches. Extending this idea to statistical inference, we propose novel techniques for calibrating confidence sets with finite-sample and asymptotic conditional coverage. These methods rely on simulated data for calibration, making them effective even in small-sample regimes or when nuisance parameters are present. Experiments show these techniques outperform existing approaches, offering practical tools for uncertainty quantification in complex settings.<\/p><p><\/div><\/p><p><span class=\"collapseomatic \" id=\"id6ae5ce050e414\"  tabindex=\"0\" title=\"Semin\u00e1rio 17\/12\/2024 - Profa. Dra. Patr\u00edcia Klarmann Ziegelmann\"    >Semin\u00e1rio 17\/12\/2024 &#8211; Profa. Dra. Patr\u00edcia Klarmann Ziegelmann<\/span><div id=\"target-id6ae5ce050e414\" class=\"collapseomatic_content \"><\/p><p><strong>T\u00edtulo:<\/strong> An\u00e1lise de Sobreviv\u00eancia em C\u00e2ncer com Base em Dados Populacionais: Desafios e Perspectivas<\/p><p><strong>Resumo:\u00a0<\/strong>O c\u00e2ncer continua sendo uma das maiores causas de mortalidade no mundo e no Brasil. Mais do que conhecer a incid\u00eancia e a mortalidade por c\u00e2ncer \u00e9 importante entender a sobreviv\u00eancia de modo a avaliar as linhas de cuidado com o paciente. Os desafios pr\u00e1ticos e metodol\u00f3gicos para estima\u00e7\u00e3o e compara\u00e7\u00e3o de taxas de sobreviv\u00eancia s\u00e3o in\u00fameros. V\u00e3o desde o estabelecimento padronizado da defini\u00e7\u00e3o do marco inicial de seguimento (data do diagn\u00f3stico ou data da cirurgia, por exemplo), passando pela cobertura e seguimento populacional at\u00e9 o entendimento dos m\u00e9todos estat\u00edsticos adequados. Assim, o objetivo deste semin\u00e1rio \u00e9 apresentar o cen\u00e1rio da an\u00e1lise de sobreviv\u00eancia ao c\u00e2ncer no Brasil enfatizando as metodologias estat\u00edsticas propostas na literatura. Ser\u00e3o apresentadas defini\u00e7\u00f5es, semelhan\u00e7as e diferen\u00e7as dos tipos de taxas de sobreviv\u00eancia comumente utilizadas: global, c\u00e2ncer espec\u00edfica, relativa e l\u00edquida. Ser\u00e3o comparados os estimadores Kaplan-Meier, Ederer II e Pohar-Perme atrav\u00e9s de exemplo com dados de mundo real e fict\u00edcios.<\/p><p><\/div><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"site-sidebar-layout":"default","site-content-layout":"default","ast-global-header-display":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"default","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","footnotes":""},"_links":{"self":[{"href":"https:\/\/www.ufrgs.br\/ppgest\/wp-json\/wp\/v2\/pages\/1559"}],"collection":[{"href":"https:\/\/www.ufrgs.br\/ppgest\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.ufrgs.br\/ppgest\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.ufrgs.br\/ppgest\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.ufrgs.br\/ppgest\/wp-json\/wp\/v2\/comments?post=1559"}],"version-history":[{"count":40,"href":"https:\/\/www.ufrgs.br\/ppgest\/wp-json\/wp\/v2\/pages\/1559\/revisions"}],"predecessor-version":[{"id":2295,"href":"https:\/\/www.ufrgs.br\/ppgest\/wp-json\/wp\/v2\/pages\/1559\/revisions\/2295"}],"wp:attachment":[{"href":"https:\/\/www.ufrgs.br\/ppgest\/wp-json\/wp\/v2\/media?parent=1559"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}