On two-stage Monte Carlo tests of composite hypotheses
MetadataShow full item record
A major weakness of the classical Monte Carlo test is that it is biased when the null hypothesis is composite. This problem persists even when the number of simulations tends to infinity. A standard remedy is to perform a double bootstrap test involving two stages of Monte Carlo simulation: under suitable conditions, this test is asymptotically exact for any fixed significance level. However, the two-stage test is shown to perform poorly in some common applications: for a given number of simulations, the test with the smallest achievable significance level can be strongly biased. A 'balanced' version of the two-stage test is proposed, which is exact, for all achievable significance levels, when the null hypothesis is simple, and which performs well for composite null hypotheses.
Showing items related by title, author, creator and subject.
Developing completion criteria for rehabilitation areas on arid and semi-arid mine sites in Western AustraliaBrearley, Darren (2003)Continued expansion of the gold and nickel mining industry in Western Australia during recent years has led to disturbance of larger areas and the generation of increasing volumes of waste rock. Mine operators are obligated ...
Evidence-based evaluation of programme interventions to achieve positive community integration outcomes for adults with acquired brain injuryParvaneh, Shahriar (2010)Background. The growing population of people with acquired brain injury (ABI) requires a strong focus on clients to be integrated into the community in order to use their productive skills in society, to help them live ...
Mann, Reinier Matthew (2000)Surfactants are one of the more ubiquitous contaminants in aquatic systems. Their importance as toxic components of pesticide formulations has, however, been largely overlooked. Amphibians particularly, as inhabitants of ...