Abstract:
One of the main differences between classical statistics and Bayesian statistics in that the latter can utilize the prior information in a formal way. This information can be quantified in terms of a probability distribution, which is known as the prior distribution. The parameters of the prior distribution are called the hyper-parameters. The objective of this paper is to provide a method based on the prior predictive distribution to elicit the hyper-parameters of the density for the parameters of the Rao-Kupper model for paired comparison data. Winkler [12] illustrates the use of the predictive distribution for eliciting the hyper-parameters of the prior distribution for the Bernoulli, normal and normal linear regression models. Other authors who adopted this view include Chaloner and Duncan [6]; Kadane [9]; Kadane et al. [10] and Winkler [12].
Page(s):
71-78
DOI:
DOI not available
Published:
Journal: Islamabad Journal of Science, Volume: 13, Issue: 1, Year: 2003