ERIC Number: ED437399
Record Type: Non-Journal
Publication Date: 1999-Nov
Reference Count: N/A
Uses and Misuses of the Correlation Coefficient.
Onwuegbuzie, Anthony J.; Daniel, Larry G.
The purpose of this paper is to provide an in-depth critical analysis of the use and misuse of correlation coefficients. Various analytical and interpretational misconceptions are reviewed, beginning with the egregious assumption that correlational statistics may be useful in inferring causality. Additional misconceptions, stemming from researchers' failure to recognize that correlation coefficients are specific cases of the general linear model (GLM), and, therefore, bounded by GLM assumptions, are also discussed. Other inappropriate practices are highlighted, including failure to: (1) consider the statistical assumptions underlying correlation coefficients; (2) interpret confidence intervals and effect sizes of correlation coefficients; (3) interpret p-calculated values in light of familywise Type 1 error; (4) consider the power of tests of hypotheses; (5) consider whether outliers are inherent in the data set; (6) recognize how measurement error can affect correlation coefficients; and (7) evaluate empirically the replicability of correlation coefficients. A heuristic example is used to illustrate how jackknife and bootstrap methods can identify unstable correlation coefficients derived from a given sample. (Contains 2 tables, 1 figure, and 80 references.) (Author/SLD)
Publication Type: Reports - Evaluative; Speeches/Meeting Papers
Education Level: N/A
Authoring Institution: N/A