• Medientyp: E-Artikel
  • Titel: Generalized Neyman-Pearson Lemma via Convex Duality
  • Beteiligte: Cvitanić, Jakša; Karatzas, Ioannis
  • Erschienen: International Statistics Institute / Bernoulli Society, 2001
  • Erschienen in: Bernoulli, 7 (2001) 1, Seite 79-97
  • Sprache: Englisch
  • ISSN: 1350-7265
  • Entstehung:
  • Anmerkungen:
  • Beschreibung: We extend the classical Neyman-Pearson theory for testing composite hypotheses versus composite alternatives, using a convex duality approach, first employed by Witting. Results of Aubin and Ekeland from non-smooth convex analysis are used, along with a theorem of Komlós, in order to establish the existence of a max-min optimal test in considerable generality, and to investigate its properties. The theory is illustrated on representative examples involving Gaussian measures on Euclidean and Wiener space.
  • Zugangsstatus: Freier Zugang