O Instituto de Ciências Matemáticas e de Computação (ICMC), da USP São Carlos, recebe inscrições para o minicurso R Programming and Mixtures, a ser ministrado por Jochen Einbeck, da Universidade de Durham, no Reino Unido. O minicurso ocorrerá nesta segunda-feira, 17 de dezembro, das 8 às 18 horas no Lab7, situado no bloco ICMC-6.
As inscrições são gratuitas podem ser feitas por meio de formulário eletrônico. As vagas são limitadas e será obedecida a ordem de chegada.
Segue abaixo o resumo do minicurso, em inglês:
 |
| Dr. Jochen Einbeck (foto: site da universidade) |
This one-day course, developed by Dr Jochen Einbeck (Durham University, UK) and Professor John Hinde (NUI Galway, Ireland), consists of two parts, where the first part refreshes generic R programming skills, while the goal of the second part is the practical implementation of inferential tools for finite Gaussian mixture modelling.
The workshop assumes basic working knowledge with R, though it does not require advanced programming skills. More specifically, the workshop begins with recalling basic tools and concepts which are useful for R programming in general; these include: workspace handling, reading in data files, extracting information from vectors and matrices, basic operations with data frames (such as ordering); basic programming skills such as as if/then, while, for, and apply, and the construction of functions.
In a short lecture to the beginning of the second part, the workshop turns to Finite Gaussian Mixture models. The idea of `complete data' (assuming the unknown component memberships to be known) is explained, based on which the complete likelihood is constructed and maximized. It is demonstrated how the resulting estimators can be incorporated into an EM algorithm, which is used to estimate all parameters of the mixture model. Using skills acquired in the first part of the workshop, the EM algorithm is implemented in R in the practical part of the afternoon session (which requires implementation of the E--step, the M--step, and the EM wrapper function). Depending on the progress, the more advanced students can proceed with implementing a bootstrap test for the number of mixture components. The techniques are illustrated with, and applied to, real data sets taken from astronomy and the energy sector.
Mais informações na Seção de Eventos do ICMC, pelo telefone (16) 3373-9146 ou e-mail eventos@icmc.usp.br.
