[ABE-L] Kelly Gonçalves - Bayesian dynamic quantile linear models

[Hedibert Lopes]

*Data Science*











Academic Seminar



*Bayesian dynamic quantile linear models*



*Speaker:* Kelly Gonçalves
<http://www.dme.im.ufrj.br/visualizarDocente.php?idDocente=38>
*University:* Instituto de Matemática UFRJ
<http://www.dme.im.ufrj.br/index.php>

The main aim of this talk is to present a new class of models, named
dynamic quantile linear models. It combines dynamic linear models with
distribution free quantile regression producing a robust statistical
method. This class of models provides richer information on the effects of
the predictors than does the traditional mean regression and it is very
insensitive to heteroscedasticity and outliers, accommodating the
non-normal errors often encountered in practical applications. Bayesian
inference for quantile regression proceeds by forming the likelihood
function based on the asymmetric Laplace distribution and a location-scale
mixture representation of it allows finding analytical expressions for the
conditional posterior densities of the model. Thus, Bayesian inference for
dynamic quantile linear models can be performed using an efficient Markov
chain Monte Carlo algorithm or a fast sequential procedure suited for
high-dimensional predictive modeling applications with massive data.
Finally, a hierarchical extension, useful to account for structural
features in the dataset, will be also presented.

March/04/2020

*12**pm de Sao Paulo, Brazil (UTC/GMT -03:00)*

*Click here to join
<https://teams.microsoft.com/l/meetup-join/19%3ameeting_NzM3YjM2NGItNzFhNS00ZDIzLWIzZmMtM2M5MWRjNDA3YThh%40thread.v2/0?context=%7b%22Tid%22%3a%229e2f1485-3e53-4662-b1de-0c2bcb66d447%22%2c%22Oid%22%3a%221e24e2c8-6775-4429-b899-1b45a6eec8a2%22%7d>*

-- 
Hedibert Freitas Lopes, PhD
Professor of Statistics and Econometrics
INSPER - Institute of Education and Research
Rua Quatá, 300 - São Paulo, SP 04546-042 Brazil
Phone: +55 11 4504-2343
www.hedibert.org
-------------- Próxima Parte ----------
Um anexo em HTML foi limpo...
URL: <http://lists.ime.usp.br/pipermail/abe/attachments/20210303/54bec7c3/attachment.htm>