Discrimination Based on an Odds Ratio Parameterization

摘要: SUMMARY It is argued that the association of any two random elements with positive joint probability density function characterized by its odds ratio function. The impact this fundamental result explored in applications. In Bayesian analyses it between an observable variable and a parameter primary interest. multivariate analysis vectors investigated. If are strongly related corresponding conditional distributions can well be separated. A concept dependence therefore implies approach to solving problems discrimination. Discrimination based on characterization exemplified inference analysis.