Comparison of experimental designs for normal and gamma distributions

• Autores: Víctor Manuel Casero Alonso, Sergio Pozuelo Campos, Mariano Amo Salas
• Localización: Proceedings of the 35th International Workshop on Statistical Modelling : July 20-24, 2020 Bilbao, Basque Country, Spain / Itziar Irigoien Garbizu (ed. lit.), Dae-Jin Lee (ed. lit.), Joaquín Martínez Minaya (ed. lit.), María Xosé Rodríguez Álvarez (ed. lit.), 2020, ISBN 978-84-1319-267-3, págs. 306-309
• Idioma: inglés
• Enlaces
  • Texto Completo Libro
• Resumen

  • The aim of this work is to show the e ect of misspeci cation in the probability distribution on optimal design. A generalized Fisher information matrix is obtained using the elemental information matrix, which includes information on the probability distribution of the response variable. Relevant theoretical results were obtained, for di erent regression models, comparing heteroscedastic gamma and normal distributions. Finally a practical case which considers a 4- parameter Hill dose-response model is used.