Abstract
Admissibility of prediction intervals is considered in a specified family. It is shown that the best invariant prediction interval is strongly admissible in a location family and in a scale family. Though the similar result has not been obtained for a location and scale family, the best invariant prediction interval for a normal distribution is shown to be weakly admissible.
Similar content being viewed by others
References
Cohen, A. (1972). Improved confidence intervals for the variance of a normal distribution,J. Amer. Statist. Assoc.,67, 382–385.
Hooper, P. M. (1986). Invariant prediction regions with smallest expected measure,J. Multivariate Anal.,18, 117–126.
Joshi, V. M. (1966). Admissibility of confidence intervals,Ann. Math. Statist.,37, 629–638.
Joshi, V. M. (1970). Admissibility of invariant confidence procedures for estimating a location parameter,Ann. Math. Statist.,41, 1568–1581.
Patel, J. K. (1989). Prediction intervals—a review,Comm. Statist. Theory Methods,18, 2393–2465.
Takada, Y. (1979). The shortest invariant prediction interval from the largest observation from the exponential distribution,J. Japan Statist. Soc.,9, 87–91.
Takada, Y. (1983). Invariant prediction regions of future observations,Kumamoto Journal of Science (Mathematics),15, 79–89.
Takeuchi, K. (1975).Statistical Prediction Theory, Baihūkan, Tokyō (in Japanese).
Author information
Authors and Affiliations
About this article
Cite this article
Takada, Y. Admissibility of prediction intervals. Ann Inst Stat Math 47, 119–128 (1995). https://doi.org/10.1007/BF00773416
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF00773416