BSBT: BSBT: Bayesian Spatial Bradley-Terry

In BSBT: The Bayesian Spatial Bradley--Terry Model

BSBT: Bayesian Spatial Bradley–Terry

Description

An implementation of the Bayesian Spatial Bradley–Terry (BSBT) model. It can be used to investigate data sets where judges compared different objects. It constructs a network to describe how the objects are connected, and then places a correlated prior distribution on the quality parameter for each object, based on the network. The package includes MCMC algorithms to estimate the quality parameters.

Covariance Functions

The covariance functions can be used to construct the Multivariate Normal prior distribution. The prior distribution includes a constraint, where a linear combination of the parameters can be specified.

There are two functions:

1. constrained_adjacency_covariance_function creates a covariance matrix using a network based metric, and

2. constrained_covariance_function creates a matrix

   using the Euclidean distance metric.
   

MCMC functions

The main MCMC function is run_mcmc, but in cases where there are different types of judges the function run_symmetric_mcmc can be used to analyse how the different types behave.

BSBT documentation built on Aug. 9, 2022, 5:06 p.m.