Significance indices for contingency tables

• Grant number: 12/16669-4
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: December 01, 2012
• End date: November 30, 2014
• Field of knowledge: Physical Sciences and Mathematics - Probability and Statistics - Statistics
• Principal Investigator: Adriano Polpo de Campos
• Grantee: Natália Lombardi de Oliveira
• Host Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil

Abstract

Our goal in this project is to study two significant indices of precise hypotheses for contingency tables, the p-value and the e-value. We will consider the generalized likelihood ratio test (GLRT) exact p-value instead of the usual asymptotic approximations. The e-value is a Bayesian significance indice that has a simple calculation and doesn't depend on prior assumptions for the null hypothesis. Based on these two indices, we'll work toward a way to calculate an exact value for the GLRT, comparing it with the e-value and discussing the asymptotic methods’ relevance, verifying the existence of a relation between these two indices.(AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

OLIVEIRA, NATALIA L.; PEREIRA, CARLOS A. DE B.; DINIZ, MARCIO A.; POLPO, ADRIANO. A discussion on significance indices for contingency tables under small sample sizes. PLoS One, v. 13, n. 8, AUG 2 2018. (12/16669-4)