MEASURING LOCATION EFFECTS FROM FACTORIAL-EXPERIMENTS WITH A DIRECTIONAL RESPONSE

Because much of the data motivating previous research on directional s tatistics comes from observational sources, a number of unresolved iss ues remain when studying location effects from a multi-way design, In this paper, we review and clarify possible definitions of factor effec ts on a directional response, and discuss their associations with some existing methods by Watson & Williams (1956), Harrison, Kanji & Gadsd en (1986, 1988) and Fisher & Lee (1992), Problems with trying to exten d these methods to study multi-way designs are presented, and a new me thod based on the likelihood ratio test statistic is proposed, Simulat ion results demonstrate the relative performance of the methods, and a n example using industrial data illustrates the technique.