• Bayesian Reference Analysis for the Generalized Normal Linear Regression Model

      Tomazella, Vera Lucia Damasceno; orcid: 0000-0002-6780-2089; email: vera@ufscar.br; Jesus, Sandra Rêgo; email: sandrarj@ufba.br; Gazon, Amanda Buosi; orcid: 0000-0001-8140-5496; email: amandagazon@alumni.usp.br; Louzada, Francisco; orcid: 0000-0001-7815-9554; email: louzada@icmc.usp.br; Nadarajah, Saralees; email: saralees.nadarajah@manchester.ac.uk; Nascimento, Diego Carvalho; orcid: 0000-0002-3406-4518; email: diego.nascimento@uda.cl; Rodrigues, Francisco Aparecido; email: francisco@icmc.usp.br; Ramos, Pedro Luiz; orcid: 0000-0002-5387-2457; email: pedrolramos@usp.br (MDPI, 2021-05-12)
      This article proposes the use of the Bayesian reference analysis to estimate the parameters of the generalized normal linear regression model. It is shown that the reference prior led to a proper posterior distribution, while the Jeffreys prior returned an improper one. The inferential purposes were obtained via Markov Chain Monte Carlo (MCMC). Furthermore, diagnostic techniques based on the Kullback–Leibler divergence were used. The proposed method was illustrated using artificial data and real data on the height and diameter of Eucalyptus clones from Brazil.