Dynamic Bayesian beta models

  • Authors:
  • C. Q. da-Silva;H. S. Migon;L. T. Correia

  • Affiliations:
  • Department of Statistics, University of Brasília-UnB, Brasília 70910-900, Brazil;Department of Statistics, Federal University of Rio de Janeiro, Rio de Janeiro 21.945-970, Brazil;Department of Statistics, University of Brasília-UnB, Brasília 70910-900, Brazil

  • Venue:
  • Computational Statistics & Data Analysis
  • Year:
  • 2011

Quantified Score

Hi-index 0.03

Visualization

Abstract

We develop a dynamic Bayesian beta model for modeling and forecasting single time series of rates or proportions. This work is related to a class of dynamic generalized linear models (DGLMs), although, for convenience, we use non-conjugate priors. The proposed methodology is based on approximate analysis relying on Bayesian linear estimation, nonlinear system of equations solution and Gaussian quadrature. Intentionally we avoid MCMC strategy, keeping the desired sequential nature of the Bayesian analysis. Applications to both real and simulated data are provided.