NEARLY OPTIMAL TESTS WHEN A NUISANCE PARAMETER IS PRESENT UNDER THE NULL HYPOTHESIS

135 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Low-Frequency Econometrics (2015, methodology): “Numerical methods can alternatively be used to approximate the LFD (see Elliott, Müller, and Watson (2015) for discussion and examples), and we will utilize that approach here.”
Factorial Designs, Model Selection, and (Incorrect) Inference in Randomized Experiments (2019, methodology): “Finally, the nearly optimal test of Elliott et al. (2015) becomes computationally prohibitive with many interactions (i.e., many nuisance parameters) and, thus, cannot be recommended for complicated factorial designs.”
Bonferroni-Based Size-Correction for Nonstandard Testing Problems (2017, unknown): “Finally, the recent work of Elliott et al. (2012) takes a somewhat different approach to some of the problems discussed here by attempting to numerically determine tests that approach an asymptotic power bound.”
HAC Corrections for Strongly Autocorrelated Time Series (2014, methodology): “Elliott, Müller, and Watson (2012) studied nonstandard problems of this kind, and showed that a test that approximately maximizes weighted average power relative to the weighting function F rejects for large values of ∫ f1,c(Y s)dF (c)/ ∫ f0,c(Y s)d̃(c), where ̃ is a numerically determined…”