Asymptotic Tests of Composite Hypotheses
Preprint
- 1 January 2003
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
Test statistics that are suitable for testing composite hypotheses are typically non-pivotal, and conservative bounds are commonly used to test composite hypothKeywords
All Related Versions
This publication has 41 references indexed in Scilit:
- PValues for Composite Null ModelsJournal of the American Statistical Association, 2000
- More Powerful Tests from Confidence Interval p ValuesThe American Statistician, 1996
- Inference in Models with Nearly Integrated RegressorsEconometric Theory, 1995
- P Values Maximized Over a Confidence Set for the Nuisance ParameterJournal of the American Statistical Association, 1994
- Tests for Parameter Instability and Structural Change With Unknown Change PointEconometrica, 1993
- Inference on Means Using the BootstrapThe Annals of Statistics, 1983
- Bayesian MethodsPublished by Springer Nature ,1974
- Further Results on Tests of Separate Families of HypothesesJournal of the Royal Statistical Society Series B: Statistical Methodology, 1962
- The Nonexistence of Certain Statistical Procedures in Nonparametric ProblemsThe Annals of Mathematical Statistics, 1956
- On the Distribution of the Likelihood RatioThe Annals of Mathematical Statistics, 1954