H. Inouzhe Valdes
Often in statistical practice a model offers a good description of
the data even though it is not the 'true' random generator. A classical test
of fit would reject such a model if the sample is large enough. We consider a
more flexible approach based on contamination neighbourhoods around a model.
Using trimming methods and the Kolmogorov metric we introduce tests of fit
to some contamination neighbourhoods which have uniformly exponentially small
type I and type II error probabilities. As as application we explore a
credibility analysis of descriptive models.
Palabras clave: trimming, Kolmogorov distance, contamination neighbourhoods, uniformly exponential, hypothesis testing
Programado
X09.3 Inferencia Estadística II
7 de septiembre de 2016 17:30
Aula 21.08
