O Programa de Pós-Graduação em Biometria e Estatística Aplicada (PPGBEA) recebe, nestas quarta e quinta-feiras (25 e 26/10), o pesquisador sérvio Milan Merkle, da University of Belgrade, que ministrará o curso Statistical depth functions and their applications in Big Data.

As aulas serão realizadas das 8h às 12h, nos dois dias, no auditório do Deinfo.

As inscrições devem ser efetuadas no local, com direito a certificado.

Confira abaixo o resumo:

Lecture

Statistical depth functions and their applications in Big Data

Milan Merkle,  Ph.D.

University of Belgrade, Serbia

In order to classify or divide in clusters a large set of data, statistical procedures use comparison of the data by the size of one or more characteristic parameters. The classical mean/variance paradigm fits nicely into a setup with Gaussian distributions, but the results can be sensitive on  small deviations from the assumed  model. In order to improve robustness, statisticians use alternative measures of centrality, like medians in scalar data.  In a multidimensional setup we can start with so called statistical depth functions and define a median set as a set of deepest points. We will consider various depth functions and their properties in high dimensions. In particular we study properties and algorithms in a popular case of so called Tukey's depth, with a focus on high-dimensional data, which is a contribution to solving specific problems in rapidly developing area of so called Big Data. A new approximate algorithm that was used in solving a problem with acoustic signals will be presented.

 Key words: Properties and algorithms, big data, statistical, statistical.