[ABE-L] Ciclo de Palestras PPG Estatística UFRJ (Hedibert Lopes - 06/10 às 15:30)

[Kelly Cristina]

Prezados,

dando continuidade ao Ciclo de Palestras do Programa de Pós-Graduação
em Estatística do IM-UFRJ, *na próxima 4a feira, 06/10/21, às 15:30*,
teremos a palestra do professor:

Hedibert Freitas Lopes (Insper)

*Título: *Decoupling Shrinkage and Selection in Gaussian Linear Factor
Analysis

*Resumo: *Factor Analysis is a popular method for modeling dependence in
multivariate data. However, determining the number of factors and obtaining
a sparse orientation of the loadings are still major challenges. In this
paper, we propose a decision-theoretic approach that brings to light the
relation between a sparse representation of the loadings and factor
dimension. This relation is done through a summary from information
contained in the multivariate posterior. To construct such summary, we
introduce a three-step approach. In the first step, the model is fitted
with a conservative factor dimension. In the second step, a series of
point-estimates with a decreasing number of factors is obtained by
minimizing an expected predictive loss function. In step three, the
degradation in utility in relation to the sparse loadings and factor
dimensions is displayed in the posterior summary. The findings are
illustrated with a simulation study, and an application to personality
data. We used different prior choices and factor dimensions to demonstrate
the flexibility of the proposed method. This is joint work with
Henrique Bolfarine (USP), Carlos Carvalho (UT Austin) and Jared Murray (UT
Austin).

A palestra ocorrerá remotamente, via plataforma Zoom (
https://us02web.zoom.us/j/81377429661?pwd=a1I1eS83eEtwSmtuWkp3a3dreG5mZz09) e
com transmissão ao vivo pelo canal do YouTube Ciclo de Palestras Estatística
UFRJ <https://www.youtube.com/channel/UCoLTqHW20Ne1qFYL2xYJOcg/featured>.

A sala será aberta em torno 10 minutos antes do início de cada sessão.
Maiores informações em: http://www.dme.ufrj.br/?page_id=3185 .

Contamos com a presença de vocês.
Atenciosamente,
-- 
*Kelly C. M. Gonçalves*
*Professora Adjunta IV*
*Departamento de Métodos Estatísticos*
*Universidade Federal do Rio de Janeiro*

*https://sites.google.com/dme.ufrj.br/kelly/
<https://sites.google.com/dme.ufrj.br/kelly/>*
-------------- Próxima Parte ----------
Um anexo em HTML foi limpo...
URL: <http://lists.ime.usp.br/pipermail/abe/attachments/20211004/74aa57fc/attachment.htm>