Large enough to matter, too small to be of consequence, or insufficient evidence? A Unified Framework Combining Minimum-Effect Significance Testing and Equivalence Testing

Is an effect found in a sample large enough to warrant inferring that the true effect in the population is large enough to be meaningful? Or is it small enough to warrant inferring that the true effect in the population is too small to be meaningful? Or does the effect not offer clear enough evidence to support either inference? This article outlines a simple yet versatile approach for answering these questions by overcoming the hurdles that prevented Minimum Effect Significance Testing (MEST) from being used widely, and by integrating it with Equivalence Testing (EqT) in a unified framework.