Ciclo de Seminario
05/11/2020 13:56
Jeniffer Sanchez (DEMA/UFC)
Quinta-feira, 12 de Novembro - 14:00h.
Na sala virtual: https://meet.google.com/jvu-htng-whd
Título: Hypothesis test in Skew-Normal regression for small sample sizes, usual test work?
Resumo: Hypothesis testing allows us to make inferences about the goal of our study from a sample to a population. We can use for this purpose the likelihood ratio test, the gradient ratio test, a more recent test, or the signed likelihood ratio test. The distribution of these statistical tests is based on asymptotic results under the null hypothesis. In the case of small samples, the asymptotic distribution leaves us to a misleading conclusion, because of that we can correct the statistical test to improve their convergence to the asymptotic distribution. We are going to present a correct statistical test for skew-normal regression models when the sample size is small. We present some theoretical and simulated results. The corrected statistical test has a good performance in terms of size and power.
SIGAA | Superintendência de Tecnologia da Informação - (84) 3342 2210 | Copyright © 2006-2024 - UFRN - sigaa07-producao.info.ufrn.br.sigaa07-producao v4.12.15