Linear hypotheses made explicit

Abstract

In testing a linear hypothesis under a general linear model, a simplest and most natural equivalent hypothesis involving only estimable parametric functions is provided, yieIding a test statistic that, is explicitly expressible in terms of the model matrices. A neat and unified treatment for the inference under a restricted linear model is then achieved

Keywords:

• equivalent hypotheses
• estimable function
• generalized inverse
• linear model
• missing cells
• orthogonal projector
• testable hypothesis
• two-factor model with one covariate