Modelos de regresión para datos de recuento con ceros truncados, ceros inflados y ceros apartados
Loading...
Identifiers
Publication date
Authors
Advisors
Tutors
Editors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
En este trabajo se han estudiado los modelos de regresión en los cuales la variable respuesta es un recuento que presenta anomalías en el valor cero, ya sea por ausencia, defecto o exceso, que nos obligan a considerar otros tipos de distribuciones de recuento diferentes a la distribución de Poisson o la Binomial Negativa. Se han estudiado las distribuciones con ceros truncados, ceros inflados y ceros apartados, que proporcionan una manera de actuar ante esas anomalías, y se han construido modelos de regresión para variables de recuento que siguen una de esas distribuciones, ilustrando su aplicación con ejemplos.
In this work we have studied regression models in which the response variable is a count that presents anomalies in the zero value, whether due to absence, defect or excess, that force us to consider different types of distributions other than the Poisson or the Negative Binomial distribution. We have studied the zero-truncated, zero-inflated and hurdle distributions, that provide us with a way to act in the event of those anomalies, and we have built regression models for each one of those distributions, illustrating their application with examples.
In this work we have studied regression models in which the response variable is a count that presents anomalies in the zero value, whether due to absence, defect or excess, that force us to consider different types of distributions other than the Poisson or the Negative Binomial distribution. We have studied the zero-truncated, zero-inflated and hurdle distributions, that provide us with a way to act in the event of those anomalies, and we have built regression models for each one of those distributions, illustrating their application with examples.
Description
78 páxinas
Keywords
Bibliographic citation
Relation
Has part
Has version
Is based on
Is part of
Is referenced by
Is version of
Requires
Sponsors
Rights
Attribution-NonCommercial-ShareAlike 4.0 International







