[ABE-L] Seminário PIPGEs com Luis Pericchi e Clarice Demétrio: 29/11 (sexta) às 14hs no ICMC-USP

[Rafael Izbicki]

Caros,

Na sexta-feira, *29 de novembro às 14:00hs*, teremos *dois* seminários do
Programa Interinstitucional de Pós-Graduação em Estatística (PIPGEs) da
UFSCar-USP.

*Local: *5-001 do ICMC-USP (São Carlos)

Seguem os detalhes.

-------------

*Nome*: Luis Pericchi, Department of Mathematics and Biostatistics,
University of Puerto Rico.

*Título*: Improved Empirical Scientific Inferences through Bayesian
Statistical Methodology: Some Substantive Examples.

*Abstract*: Empirical and Bayesian reasoning complement each other. Rather
than opposing schools of statistics here we illustrate how Bayesian
Statistics can improve Empirical Frequentist-Scientific Measures.
Illustrative Examples:
• Why does the ”impossible” happen all the time? Accurate Bayesian
Prediction of Catastrophes and Extreme Values.
• Turning Type-I errors-α into False Discovery Rates, through Bayesian
Expected Trees.
• Why ”most statistical findings turn out to be false”? Replacement of
p-values by Bayes Factors.
• Is the Extra-Sensory Perception Real? ”Do you want to reject a
Hypothesis? Take a Large Enough Sample, and Do Not Use BayesFactors”.
• If you have a data set with outliers, like in the famous Darwin’s data.
Can you make predictions weighting a Normal and an Outlier prone
Distribution, by their posterior model probabilities?
• Applications to Health Studies by Bayesian Model Averaging and Inclusion
Probabilities.
• Some of the most important questions of the world are Demographic and
Modern Demography is Probabilistic and Bayesian with Hierarchical Models
across countries (United Nations Models).

-------------

*Nome*: Clarice Demétrio, Departamento de Ciências Exatas da ESALQ/USP.

*Título*: Overdispersion models for clustered toxicological data in a
bioassay of entomopathogenic fungus.

*Abstract*: We consider discrete mortality data for groups of individuals
observed over time. The fitting cumulative mortality curves as a function
of time involves the longitudinal modeling of the multinomial response.
Typically such data exhibit overdispersion, that is greater variation than
predicted by the multinomial distribution. To model the extra-multinomial
variation (overdispersion) we consider a Dirichlet-multinomial model, a
random intercept model, and a random intercept and slope model. We
construct asymptotic and robust covariance matrix estimators for the
regression parameter standard errors. Applying this model to a specific
insect bioassay of the fungus *Beauveria bassiana*, we note some simple
relationships in the results and explore why these are simply a consequence
of the data structure. Fitted models are used to make inferences on the
effectiveness of different fungus isolates. The results are compared with a
simple empirical analysis to provide recommendations for the field use of
this fungus as a biological control.

Todos são bem vindos!


[image: seminarios.png]


          Rafael

--
Rafael Izbicki
Assistant Professor | Vice Director of Graduate Studies
Department of Statistics
Federal University of São Carlos (UFSCar)
https://rafaelizbicki.com/
www.small.ufscar.br
-------------- Próxima Parte ----------
Um anexo em HTML foi limpo...
URL: <http://lists.ime.usp.br/pipermail/abe/attachments/20241121/6f4db6c4/attachment-0001.htm>
-------------- Próxima Parte ----------
Um anexo não-texto foi limpo...
Nome: seminarios.png
Tipo: image/png
Tamanho: 408327 bytes
Descrição: não disponível
URL: <http://lists.ime.usp.br/pipermail/abe/attachments/20241121/6f4db6c4/attachment-0001.png>