ABSTRACT
For large-scale one-sided sequential tests from independent panels, the detection of sparse signals is considered when the signals only appear in a small portion of panels. By treating the model as a mixture inverse Gaussian distribution, a supplementary local test is proposed by first testing the existence of the signal and then the strength of signals. The results are then extended to the truncated one-sided test case. A second-order corrected test is studied under the discrete normal model, along with simulations results for the power and a real data example.
Acknowledgments
The comments and suggestions from two referees are greatly appreciated.
Conflict of interest
The author confirms that this article content has no conflict of interest.