Downloads provided by UsageCounts
handle: 10902/20124
RESUMEN: Normalidad (un conjunto de observaciones son muestreadas de un Proceso Gaussiano) es un supuesto importante en una gran cantidad de modelos estadísticos. Debido a eso, desarrollar procedimientos para corroborar estos supuestos es un tema que ha ganado popularidad en los últimos años. Existe una gran cantidad de literatura para el caso de variables aleatorias independientes e identicamente distribuidas, pero, este no es el caso en el contexto de procesos estocásticos estacionarios, donde el supuesto de independencia no se mantiene. Algunas prue- bas de hipótesis han sido propuestas a traves de los años para resolver esta problemática. El objetivo de este trabajo es presentar una discusión de las pruebas más utilizadas para probar normalidad en procesos estacionarios, tales como Epps, Lobato y Velasco, las proyecciones aleatorias, y Psaradakis y Vavra. Para diagnostico de modelos en un enfoque Bayesiano, proponemos una metodología alternativa para la corroboración de supuestos inspirada en los resultados del método de las proyecciones aleatorias con prometedores resultados. Adicional- mente, presentamos nuestro implementado paquete nortsTest, un paquete en R que realiza las pruebas mencionadas anteriormente.
ABSTRACT: Normality (a set of observations being sampled from a Gaussian process) is an important as- sumption in a wide variety of statistical models. Therefore, developing procedures for testing this assumption is a topic that has gained popularity over several years. Extensive literature exists on goodness of fit tests for normality under the assumption of independent identical distributed random variables. However, this is not the case for the context of stationary stochastic process, case in which the independence assumption is violated. For this matter, several tests have been proposed over the years. The aim of this work is to present a discus- sion and references of the most common tests for normality in stationary processes, such as Epps, Lobato and Velasco, the random projections, and Psaradakis and Vavra. For assessing model adequacy in a Bayesian approach,we propose an alternative methodology for checking model’s assumptions inspired by the random projection results with promising results, in all the designed case studies. Additionally we present our implemented nortsTest package, an R package that performs all the reviewed tests mentioned above.
Máster en Matemáticas y Computación
Stationarity, Model’s diagnostic, Procesos estocasticos, Pruebas de hipótesis, Diagnostico de modelos, Estacionaridad, Hypothesis test, Gaussian process, Stochastic process, Procesos Gaussianos
Stationarity, Model’s diagnostic, Procesos estocasticos, Pruebas de hipótesis, Diagnostico de modelos, Estacionaridad, Hypothesis test, Gaussian process, Stochastic process, Procesos Gaussianos
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
| views | 64 | |
| downloads | 105 |

Views provided by UsageCounts
Downloads provided by UsageCounts