Esse video faz parte do Curso de Estatística para Pesquisa Científica, disponível em http://rangel.eco.br A variabilidade das médias estimadas através de várias amostras repetidas da mesma população parece obedecer uma distribuição normal: valores intermediários são frequentes e valores extremos são raros. Entretanto, na verdade essas repetidas médias seguem uma distribuição de frequência chamada distribuição t de Student, que é uma irmã da distribuição normal. A distribuição t de Student leva em consideração o tamanho da amostra que foi utilizada para calcular as médias repetidas. Assim, se o tamanho da amostra for pequeno, valores de média estimada muito diferentes entre si (extremos) não serão tão raros assim, pois não seria tão incomum selecionar aleatoriamente apenas pessoas altas/baixas em uma amostra pequena. Ao contrário, se o tamanho das amostras for grande, valores calculados de médias repetidas não serão tão diferentes assim entre si, pois seria muito improvável selecionar aleatoriamente apenas pessoas altas/baixas em uma amostra muito grande. Na prática, a distribuição de frequências t de Student fica cada vez mais parecida com a distribuição normal quando o tamanho da amostra cresce. Baixe aqui o programa que eu construí para ilustrar a diferença entre a distribuição normal e a distribuição t de Student.

This official video presents the physical structure and academic achievements of the University of Campinas (Unicamp), an institution of considerable stature since its inauguration in 1966. Unicamp has dedicated itself to teaching, research, outreach and innovation in all areas of knowledge. Around five thousand students graduate each year from its degree programs. Its main campus is located in the city of Campinas, with two other campi in the nearby towns of Limeira and Piracicaba. Additionally, two secondary schools, Cotil and Cotuca, provide technical training to a large number of students in the neighboring area. The University is also an integral part of the International HUB for Sustainable Development (HIDS), a model for smart city districts, congregating governmental agencies as well as twelve other institutions, with the objective of promoting and fostering the United Nations Agenda 2030 with its 17 Sustainable Development Objectives. Unicamp also dedicates itself to public health, paying special attention to its support centers and its Clinics Hospital, responsible for serving a metropolitan area with seven million people. The University is also a pioneer in the establishment of a Human Rights Executive Board and of racial and ethnic quotas for students, a policy that transformed the profile of the Unicamp community, now more similar in diversity to the Brazilian population. 

Unicamp Institutional 

Production: Patrícia Lauretti 

Narrator: Ricardo Dahab E

English translation: Rodrigo Campos Castro 

Camera: João Ricardo – Boi, Marcos Botelho Jr. 

Art: Diohny C. Andrade 

Image Editing: Kleber Casabllanca 

Cover: Paulo Cavalheri

WESAAC 2013 - Sessão Técnica I. "Application of Workflow in Multi-Agent System Organization", por José Neri, Carlos Santos e Jomi Hubner. Data: 27/05/2013

SGI Presentation A Multi-application, Multi-workflow Approach to High Performance Computing Information Technology enabled systems, tools, and services have had profoundimpact on the practice of science and engineering research in the beginning ofthe 21st Century. The term Cyberinfrastructure is being used to describe the newresearch environments that support advanced data acquisition, data storage, datamanagement, data integration, data mining, data visualization and other computing and information processing services over the Internet. In scientific usage, Cyberinfrastructure is a technological solution to the problem of efficiently connecting data, computers, and people with the goal of enabling derivation of novel scientific theories and knowledge.To harness the full power of Cyberinfrastructure requires careful and focusedinvestments, not only in hardware and software resources, but also on training people, aiming the preparation of a science and engineering workforce with the knowledge and skills needed to create, advance, and take advantage ofthose specialized systems over the long-term.The goal of this workshop is to bring together the academic community and keyindustry partners in this broad, emerging area of computationally-enabled Science & Engineering, in order to address the common challenges faced by several disciplines in the broad area of Scientific Computing. The main idea is to review some of the many ongoing research and development programs in the general area of e-Science, stimulating discussions in strategic and methodological issues of common interest.

Presentation at the IV International Workshop on Pollutants in the Environment, 2010.

This work presents the Objective Bayesian approach for the estimation of the parameters of the generalized normal model. Simulation studies were performed to analyze the frequentist properties of credible intervals from the reference posterior distribution. The proposed methodology is illustrated in a real data set.