A discussion of a logical fallacy in the use of correlation coefficients to distinguish between alternative causal patterns as an inference tool in social science. Justification for using the technique is superficially convincing, and appears to be supportable by rigorous mathematical analysis. The fallacy of the technique stems from the fact that the conclusions reached from it are based on an assumption usually made as a mathematical convenience. This assumption is that statistical independence of residual terms in the equations represents alternative causal patterns. Unless the analyst is willing to explicitly equate independence of residuals with real-world causation, conclusions about causation drawn from causal analysis are specious. The equations used in causal analysis may be given both a causal and a statistical meaning, and there is no necessary relationship between the two. 8 pp.
This report is part of the RAND Corporation Paper series. The paper was a product of the RAND Corporation from 1948 to 2003 that captured speeches, memorials, and derivative research, usually prepared on authors' own time and meant to be the scholarly or scientific contribution of individual authors to their professional fields. Papers were less formal than reports and did not require rigorous peer review.
This document and trademark(s) contained herein are protected by law. This representation of RAND intellectual property is provided for noncommercial use only. Unauthorized posting of this publication online is prohibited; linking directly to this product page is encouraged. Permission is required from RAND to reproduce, or reuse in another form, any of its research documents for commercial purposes. For information on reprint and reuse permissions, please visit www.rand.org/pubs/permissions.
The RAND Corporation is a nonprofit institution that helps improve policy and decisionmaking through research and analysis. RAND's publications do not necessarily reflect the opinions of its research clients and sponsors.