2011/11/04_Jacobo de Uña (University of Vigo) and Daniel Yekutieli (University of Tel Aviv)

November 4th 2011

Faculty of Economic and Business Sciences | Seminar 273

SGoF: a new approach to significance in multiple testing


2011/11/04 – 12:05 h | Jacobo de Uña-Álvarez, University of Vigo.

Abstract

Multiple hypotheses testing has been addressed under several (re-)definitions of significance, starting from the familywise error rate (FWER) and considering more liberal criteria (such as the false discovery rate, FDR) in order to improve the power. In this talk I will revisit a novel approach known as Sequential Goodness-of-Fit (SGoF) test (Carvajal-Rodriguez et al, 2009) under the view of the new re-definition of significance which underlies the method. Advantages and disadvantages of SGoF’s sigificance criterion when compared to FDR will be discussed.

Bayesian selective inference


2011/11/04 – 12:50 h | Daniel Yekutieli, University of Tel Aviv.

Abstract

The term selective inference refers to marginal statistical inferences that are provided for parameters selected after viewing the data, where the selected parameters are typically the significant findings of a multiple testing procedure. I will discuss selective inference from a Bayesian perspective. I will show that if the parameter is elicited a non-informative prior, or if it is a fixed unknown constant, then it is necessary to adjust the Bayesian inference for selection. I will present a Bayesian framework for providing inference for selected parameters and Bayesian False Discovery Rate controlling methodology, that is a generalization of existing Bayesian FDR methods that are only defined in the two-group mixture model. I will illustrate the results by applying them to simulated data and data from a microarray experiment.