Prediction Intervals with the Dirichlet Prior.
FLORIDA STATE UNIV TALLAHASSEE DEPT OF STATISTICS
Pagination or Media Count:
Let X sub 1, X sub n and Y1, Y sub n be consecutive samples from a Dirichlet process on R, B the real line R with the Borel sigma field B with parameter alpha. Typically, prediction intervals employ the previous observations X sub 1, X sub n in order to predict a specified function of the future sample Y sub 1, Y sub n. Here one- and two- sided prediction intervals for at least k of N future observations are developed for the situation in which, in addition to the previous sample, there is prior information available. The information is specified via the parameter alpha of the Dirichlet process. Author
- Statistics and Probability