Multiple-use prediction and calibration for all future values: Exact simultaneous tolerance bands for multiple and polynomial regressions
Statistical Methods in Medical Research · 2026
DOI: 10.1177/09622802261470084 ↗Kurz gefasst
Fachartikel in der Zeitschrift Statistical Methods in Medical Research, 2026. Verfasst von Lingjiao Wang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics, The University of Manchester, Manchester, England, UK. Hauptthemen laut MEDLINE: Models, Statistical. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Multiple-use prediction and calibration for all future values play an important role in many areas, including health and medical research. Simultaneous tolerance bands (STBs) can be employed for these purposes. This article studies the construction of exact STBs for multiple regression over any given rectangular covariate regions and for polynomial regression over any given covariate intervals. We first fill the gap in constructing the exact STBs for multiple regression over rectangular regions. We then propose a general form of STBs and develop a method for computing the critical constants for all STBs considered, including existing ones in the literature. A new STB is also proposed for both multiple and polynomial regressions. This new STB and several existing forms are then compared under the average shift (AS) criterion. Numerical results indicate that the new STB performs best under the AS criterion and is therefore recommended. In addition, a computationally efficient algorithm is presented. Real-life examples are provided for illustration.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Mathematics, The University of Manchester, Manchester, England, UK.
- Southampton Statistical Sciences Research Institute and School of Mathematical Sciences, University of Southampton, Southampton, England, UK.
- Novartis Pharma AG, Basel, Switzerland.
- Center for Medical Data Science, Institute of Medical Statistics, Medical University of Vienna, Vienna, Austria.
ORCID-Profile: Lingjiao Wang, Yang Han, Wei Liu, Frank Bretz
Zitieren
APA
Wang, L., Han, Y., Liu, W., & Bretz, F. (2026). Multiple-use prediction and calibration for all future values: Exact simultaneous tolerance bands for multiple and polynomial regressions. Statistical Methods in Medical Research. https://doi.org/10.1177/09622802261470084
Vancouver
Wang L, Han Y, Liu W, Bretz F. Multiple-use prediction and calibration for all future values: Exact simultaneous tolerance bands for multiple and polynomial regressions. Statistical Methods in Medical Research. 2026. doi:10.1177/09622802261470084
BibTeX
@article{Wang2026,
author = {Wang, Lingjiao and Han, Yang and Liu, Wei and Bretz, Frank},
title = {Multiple-use prediction and calibration for all future values: Exact simultaneous tolerance bands for multiple and polynomial regressions},
journal = {Statistical Methods in Medical Research},
year = {2026},
doi = {10.1177/09622802261470084}
}
EUVIMED