A predictive density approach to predicting a future observable in multilevel models

David Afshartous, Jan de Leeuw

Research output: Contribution to journalArticlepeer-review

4 Scopus citations

Abstract

A predictive density function g* is obtained for the multilevel model which is optimal in minimizing a criterion based on Kullback- Leibler divergence for a restricted class of predictive densities, thereby extending results for the normal linear model (J. Amer. Statist. Assoc. 81 (1986) 196). Based upon this predictive density approach, three prediction methods are examined: multilevel, prior, and OLS. The OLS prediction method corresponds to deriving a predictive density separately in each group, while the prior prediction method corresponds to deriving a predictive density for the entire model. The multilevel prediction method merely adjusts the prior prediction method by employing a well-known shrinkage estimator from multilevel model estimation. Multilevel data are simulated in order to assess the performance of these three methods. Both predictive intervals and predictive mean square error (PMSE) are used to assess the adequacy of prediction. The multilevel prediction method outperforms the OLS and prior prediction methods, somewhat surprising since the OLS and prior prediction methods are derived from the Kullback-Leibler divergence criterion. This suggests that the restricted class of predictive densities suggested by Levy and Perng for the normal linear model may need to be expanded for the multilevel model.

Original languageEnglish (US)
Pages (from-to)149-164
Number of pages16
JournalJournal of Statistical Planning and Inference
Volume128
Issue number1
DOIs
StatePublished - Jan 15 2005
Externally publishedYes

Keywords

  • Kullback-Leibler divergence
  • Multilevel model
  • Prediction
  • Predictive density
  • Predictive interval

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'A predictive density approach to predicting a future observable in multilevel models'. Together they form a unique fingerprint.

Cite this