Posterior Distributions for Func-tions of Variance Components

• Autores: Irwin Guttman, Ulrich Menzefricke
• Localización: Test: An Official Journal of the Spanish Society of Statistics and Operations Research, ISSN-e 1863-8260, ISSN 1133-0686, Vol. 12, Nº. 1, 2003, págs. 115-123
• Idioma: inglés
• DOI: 10.1007/bf02595814
• Texto completo no disponible (Saber más ...)
• Resumen

  • This paper uses a Bayesian approach to examine the posterior distributions of linear and non-linear functions of variance components in balanced two-way analysis of variance designs. The paper shows how exact posterior distributions for such functions can be readily described using Monte Carlo simulations where independent draws from the distributions are obtained. It is thus very straightforward to obtain percentiles, means, standard deviations, and other summary measures for the posterior distributions.