DURING THE LAST 10 YEARS, A NUMBER OF NEW TECHNIQUES FOR THE ANALYSIS OF NONMETRIC DATA HAVE BEEN DEVELOPED THAT ARE EQUIVALENT TO CLASSIC METRIC APPROACHES IN STATISTICAL RIGOR BUT ARE BASED ON ASSUMPTIONS THAT WILL GENERALLY BE MET BY MOST DATA THAT ARISE IN SURVEYS. LITTLE DISAGREEMENT EXISTS AMONG METHODOLOGISTS THAT ORDINARY REGRESSION SHOULD NOT BE USED WITH DUMMY DEPENDENT VARIABLES. WHEN THE ASSUMPTIONS OF HOMOSCEDASTICITY AND NORMAL DISTRIBUTION OF THE DEPENDENT VARIABLE ARE NOT MET, INVALID INFERENCES OFTEN RESULT; NEVERTHELESS, THIS APPROACH IS STILL VERY POPULAR WITH RESEARCHERS MORE INTERESTED IN THE SUBSTANTIVE ISSUES THAN THE METHODOLOGY. EXAMINING DIFFERENCES AND SIMILARITIES BETWEEN DUMMY DEPENDENT VARIABLE REGRESSION AND THE NEW TECHNIQUES IS AN URGENT TASK AIMED AT IMPROVING THE DATA ANALYSES DONE BY THE SUBSTANTIVELY ORIENTED RESEARCHER. IN THIS ARTICLE, ANOTHER TECHNIQUE IS DISCUSSED: A SIMPLE VERSION OF THE WEIGHTED LEAST SQUARES APPROACH DEVELOPED BY GRIZZLE, STARMER, AND KOCH (GSK). THIS SIMPLE VERSION OF THE GSK APPROACH USES A SATURATED MODEL WHERE ALL INTERACTIONS, AS WELL AS DIRECT EFFECTS, ARE POSTED. THE NEW TECHNIQUE IS COMPARED TO THE USUAL DUMMY REGRESSION APPROACH. MATHEMATICAL EQUATIONS AND AN ILLUSTRATIVE APPLICATION OF THE TECHNIQUE ARE PROVIDED, ALONG WITH NOTES.