The Contribution of Difference Score to Prediction,
Abstract
The difference between two variables is viewed as a legitimate way to operationalize such concepts as deficiency, gain, and growth. However, it is pointed out that in a correlational analysis it is important to distinguish between the effect of the difference score on a third variable and the degree of prediction that is possible with the optimal combination of the component variables. In this regard it is suggested that the effect of the difference between two variables be evaluated within the context of their optimally weighted composite. Illustrations of three ways in which the difference between two variables may contribute to the prediction of a third are discussed. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Dec 01, 1977
- Accession Number
- ADA100228
Entities
People
- William Pugh
Organizations
- Naval Health Research Center