The expected sample size of some tests of power one

From MaRDI portal
Publication:1222490

DOI10.1214/aos/1176342704zbMath0318.62069OpenAlexW1970385173MaRDI QIDQ1222490

David O. Siegmund

Publication date: 1974

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1214/aos/1176342704




Related Items (25)

Likelihood Ratio Identities and Their Applications to Sequential AnalysisA simple comparision of mixture vs. nonanticipating estimationA nonparametric sequential test with power 1 for the mean of Lévy-stable laws with infinite varianceUniversal inferenceGeneral optimal stopping with linear costAlways Valid Inference: Continuous Monitoring of A/B TestsConfidence sequences with composite likelihoodsEncounters with Martingales in Statistics and Stochastic OptimizationGame-theoretic statistics and safe anytime-valid inferenceDetecting changes in a multiparameter exponential family by using adaptive CUSUM procedureHerbert Robbins and sequential analysisSequential Change-Point Detection Procedures That are Nearly Optimal and Computationally SimpleImportance Sampling for Generalized Likelihood Ratio Procedures in Sequential AnalysisNearly optimal sequential tests of composite hypotheses revisitedLaws of the iterated logarithm for sample moments and applicationsA nonparametric sequential test with power 1 for the ruin probability in some risk modelsTime-uniform, nonparametric, nonasymptotic confidence sequencesProbabilistic Bisection Converges Almost as Quickly as Stochastic ApproximationAsymptotic optimality of double sequential mixture likelihood ratio testTesting exchangeability: fork-convexity, supermartingales and e-processesNonasymptotic sequential tests for overlapping hypotheses applied to near-optimal arm identification in bandit modelsNonanticipating estimation applied to sequential analysis and changepoint detectionAsymptotic densities of stopping times associated with tests of power oneA martingale approach for detecting the drift of a Wiener processMatrices -- compensating the loss of anschauung




This page was built for publication: The expected sample size of some tests of power one