INFORMATIVE VERSUS NON-INFORMATIVE PRIOR
DISTRIBUTIONS AND THEIR IMPACT ON THE ACCURACY OF BAYESIAN INFERENCE Cover Image

INFORMATIVE VERSUS NON-INFORMATIVE PRIOR DISTRIBUTIONS AND THEIR IMPACT ON THE ACCURACY OF BAYESIAN INFERENCE
INFORMATIVE VERSUS NON-INFORMATIVE PRIOR DISTRIBUTIONS AND THEIR IMPACT ON THE ACCURACY OF BAYESIAN INFERENCE

Author(s): Wioletta Grzenda
Subject(s): Economy, Business Economy / Management, Accounting - Business Administration
Published by: Główny Urząd Statystyczny
Keywords: Bayesian approach; regression models; a priori information; MCMC;

Summary/Abstract: In this study the benefits arising from the use of the Bayesian approach topredictive modelling will be outlined and exemplified by a linear regressionmodel and a logistic regression model. The impact of informative and noninformativeprior on model accuracy will be examined and compared. The datafrom the Central Statistical Office of Poland describing unemployment inindividual districts in Poland will be used. Markov Chain Monte Carlo methods(MCMC) will be employed in modelling.

  • Issue Year: 17/2016
  • Issue No: 4
  • Page Range: 763-780
  • Page Count: 18
  • Language: English
Toggle Accessibility Mode