Published
2008-07-01
DISEÑOS EXPERIMENTALES SECUENCIALES PARA MODELOS LOGÍSTICOS DE REGRESIÓN
EXPERIMENTAL SEQUENTIAL DESIGNS FOR LOGISTIC REGRESSION MODELS
Keywords:
diseño factorial, metodología de superficie de respuesta, diseño de experimentos secuenciales, modelo lineal generalizado, regresión logística, matriz de información de Fisher (es)Factorial Design, Response Surface Design, Sequential Design of Experiments, Generalized Linear Model, Logistic Regression, Fisher Information Matrix (en)
Cuando los supuestos habituales de normalidad y varianza constante no se cumplen (e.g. en procesos de Bernoulli o binomiales), el problema de la elección de diseños adecuados ocasiona cierta dificultad a los experimentadores, especialmente cuando lo que se persigue es una exploración secuencial del proceso. Este artículo está basado en De Zan (2006), en donde se proponen dos criterios para evaluar estrategias de diseño. Una de ellas toma en cuenta la cantidad de información contenida en el modelo ajustado, mientras que la otra explora la información contenida en las mejores condiciones de experimentación encontradas en el modelo ajustado. Se desarrolla un ejemplo simulado con el paquete R acerca de cómo funcionan estas estrategias.
When the usual hypotheses of normality and constant variance do not hold (e.g. in binomial or Bernoulli processes), the problem of choosing appropriate designs creates problems to researches when pursuing a sequential exploration of process. This paper is based on De Zan (2006), where the author proposes two criteria to evaluate design strategies, that take the amount of information as the main evaluation tool. One into account the information of the fitted model, and the other explores the information that is contained on the approximation of a set of the best conditions of factors found on a fitted model. An example of how these strategies work is also given through a simulation using R software.
License
Copyright (c) 2008 Revista Colombiana de Estadística

This work is licensed under a Creative Commons Attribution 4.0 International License.
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).






