Comments on: hybrid semiparametric Bayesian networks

• Stefan Sperlich ^[1]
  1. [1] Université de Genève

     Université de Genève

     Genève, Suiza

     
• Localización: Test: An Official Journal of the Spanish Society of Statistics and Operations Research, ISSN-e 1863-8260, ISSN 1133-0686, Vol. 31, Nº. 2, 2022, págs. 335-339
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • This note comments on the article of David Atienza, Pedro Larrañaga and Concha Bielza in which they first review recent contributions to Bayesian networks and then introduce a new hybrid version. It combines parametric and nonparametric density estimates for continuous variables by simultaneously allowing for discrete parents. We discuss straightforward extensions of the linear Gaussian parts and potential smoothing over the outcomes of discrete parents and conclude with some minor comments.