Files
Abstract
Excerpts from the report Introduction: Considerable use has been made of the graphic method of correlation during the past 10 years, particularly in the field of agricultural economics. The method has been popular for several reasons: (1) It indicates graphically the "net" relationships between the variables included in the study, (2) it has been thought to be an exceedingly simple and flexible method of studying curvilinear relationships, (3) it is a relatively simple mechanical substitute for mathematical calculations. Although it is now more than 10 years since L. H. Bean’s article on the graphic method of correlation was published, some confusion still exists among the users of the method regarding the correct interpretation of the results obtained in terms of standard mathematical coefficients. It is the purpose of this paper to examine the meaning of the various steps involved in the graphic correlation procedure from the point of view of the Least Squares method. This article deals with the graphic method as applied to linear relationships or relationships which can be made linear by transformation.