ERIC Number: ED233059
Record Type: RIE
Publication Date: 1983-Mar
Reference Count: 0
A Method for Maximizing the Internal Consistency Coefficient Alpha.
This paper presents three different ways of computing the internal consistency coefficient alpha for a same set of data. The main objective of the paper is the illustration of a method for maximizing coefficient alpha. The maximization of alpha can be achieved with the aid of a principal component analysis. The relation between alpha max. and the first eigenvalue of a principal component analysis is presented. Alpha reaches its optimum value for a given set of items when each standardized item is weighted by its respective saturation coefficient under the first principal component. An example shows how one can calculate alpha, alpha standardized and alpha max. Though statistical weighting of the items offers the possibility of increasing the internal consistency of a scale, the different importances given to each item should not be too far from a rational weighting based the nature of the items or other theoretical considerations. (Author)
Publication Type: Speeches/Meeting Papers; Reports - Research
Education Level: N/A
Authoring Institution: N/A
Identifiers: Alpha Coefficient; Eigenvalues; Internal Consistency; Principal Components Analysis; Weighting (Statistical)
Note: Paper presented at the Annual Meeting of the American Educational Research Association (67th, Montreal, Quebec, April 11-15, 1983).