Frequentist prediction intervals and predictive distributions

被引:119
作者
Lawless, JF [1 ]
Fredette, M
机构
[1] Univ Waterloo, Dept Stat & Actuarial Sci, Waterloo, ON N2L 3G1, Canada
[2] HEC Montreal, Serv Enseignement Methodes Quantitat Gest, Montreal, PQ H3T 2AT, Canada
关键词
calibration; confidence distribution; coverage probability; Kullback-Leibler distance; pivotal;
D O I
10.1093/biomet/92.3.529
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
We consider parametric frameworks for the prediction of future values of a random variable Y, based on previously observed data X. Simple pivotal methods for obtaining calibrated prediction intervals are presented and illustrated. Frequentist predictive distributions are defined as confidence distributions, and their utility is demonstrated. A simple pivotal-based approach that produces prediction intervals and predictive distributions with well-calibrated frequentist probability interpretations is introduced, and efficient simulation methods for producing predictive distributions are considered. Properties related to an average Kullback-Leibler measure of goodness for predictive or estimated distributions are given. The predictive distributions here are shown to be optimal in certain settings with invariance structure, and to dominate plug-in distributions under certain conditions.
引用
收藏
页码:529 / 542
页数:14
相关论文
共 24 条
[1]  
AITCHISON J, 1975, BIOMETRIKA, V62, P547, DOI 10.1093/biomet/62.3.547
[2]  
Aitchison J., 1975, Statistical Prediction Analysis
[3]  
[Anonymous], 1993, Predictive Inference
[4]  
Barndorff-Nielsen O. E., 1996, Bernoulli, V2, P319
[5]  
Barndorff-Nielsen OE., 1994, INFERENCE ASYMPTOTIC
[6]   CALIBRATING PREDICTION REGIONS [J].
BERAN, R .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1990, 85 (411) :715-723
[7]  
Bjornstad JF., 1990, Stat. Sci, V5, P242, DOI [10.1214/ss/1177012175, DOI 10.1214/SS/1177012175]
[8]  
Cox D.R., 1975, PERSPECTIVES PROBABI, P47
[9]  
Davison A. C., 1997, BOOTSTRAP METHODS TH, DOI 10.1017/CBO9780511802843
[10]  
Efron B, 1998, STAT SCI, V13, P95