Summary
It is well known that the problem to obtain a maximin size- α test Φ* can be formulated as an infinite linear programming problem, if the sample space or the parameter space is not finite. To approximate Φ* a series of finite linear programming problems is constructed such that its solution is feasable for the infinite problem and you can get an upper bound for the distance to an optimal solution.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
Literatur
Krafft und Wittings: Optimale Tests und ungünstigste Verteilungen. Z.Wahrscheinlichkeitstheorie verw. Geb. 7 289–302 (1967)
Wittings: Mathematische Statistik. Eine Einführung in Theorie und Methoden, Stuttgart: Teubner 1966
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1974 Physica-Verlag, Rudolf Liebing KG, Würzburg
About this paper
Cite this paper
Hülsmann, J. (1974). Zur Approximation von Maximintests. In: Gessner, P., Henn, R., Steinecke, V., Todt, H. (eds) DGOR Papers of the Annual Meeting 1973 / Vorträge der Jahrestagung 1973. Proceedings in Operations Research, vol 1973. Physica-Verlag HD. https://doi.org/10.1007/978-3-642-99747-1_26
Download citation
DOI: https://doi.org/10.1007/978-3-642-99747-1_26
Publisher Name: Physica-Verlag HD
Print ISBN: 978-3-7908-0138-5
Online ISBN: 978-3-642-99747-1
eBook Packages: Springer Book Archive