Abstract

Standard approaches for testing whether a multivariate normal mean vector is zero are agnostic regarding alternative hypothesis. In some settings, subject-matter considerations will imply structure on the alternative of the mean vector, for example, that each element of the mean vector is positive, or that the elements are monotonically increasing. Nonstandard multivariate tests incorporate this knowledge about the alternative hypothesis to derive more powerful tests. This article provides a brief overview of selected nonstandard multivariate tests. Keywords: likelihood ratio test; order restriction

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call