20/05/2016 - Coerência em Testes de Hipótese - Palestrante: Luís Gustavo Esteves (IME-USP)
Quando |
20/05/2016 das 14h00 até 15h45 |
---|---|
Onde | Sala de seminários (sala 38) do DEs-UFSCar |
Adicionar evento ao calendário |
vCal iCal |
Seminário Conjunto UFSCar/ICMC
LOCAL: Sala de seminários (sala 38) do DEs-UFSCar, São Carlos, SP.
TITULO: Coerência em Testes de Hipótese
PALESTRANTE: Luís Gustavo Esteves, do IME-USP
RESUMO:
Multiple hypothesis testing, an important quantitative tool to report the results of scientific inquiries, frequently leads to contradictory conclusions. For instance, in an ANOVA setting, the same data set can lead one to reject the equality of two means, but at the same time to not reject the hypothesis these means are (both) equal to zero. These two conclusions violate the coherence principle introduced by Gabriel [1969], and lead to results that are difficult to communicate to practitioners of statistical methods. Although this situation is common in the daily life of statisticians, it is usually neglected in courses of statistics. In this work, we discuss this topic by investigating through a few examples whether several standard test procedures are coherent. We also discuss the relationship between coherent tests and measures of support. Finally, we show how a Bayesian decision-theoretic framework can be used to build coherent tests.