Hi On 3 Dec 2001, Karl L. Wuensch wrote: > I think that phrase has created much misunderstanding. I try > to convince my students that correlation is necessary but not > sufficient for establishing a causal relationship.
And I teach that NEITHER presence NOR absence of _simple_ correlation can be used to infer much about causality. The reasoning is the same in both cases. In the case of presence of a correlation between X and Y, another variable might be confounded with X and responsible for the observed r. In the case of the absence of a correlation between X and Y, another variable might be confounded with X and masking its influence, producing the observed r. An example of the latter that I am fond of is the relatively low r between amount of time spent studying and grades. The effect of study time is masked by its negative correlation with ability (i.e., IQ), which tends to be positively correlated with grades. In essence, brighter people spend less time studying (perhaps because they can obtain good grades without more study time). Multiple regression with both study time and ability reveals the robust effects of study time (and enhances the effect of ability as well). So, depending on precisely what Karl means by "correlation is necessary," I'd have to disagree strongly. Best wishes Jim ============================================================================ James M. Clark (204) 786-9757 Department of Psychology (204) 774-4134 Fax University of Winnipeg 4L05D Winnipeg, Manitoba R3B 2E9 [EMAIL PROTECTED] CANADA http://www.uwinnipeg.ca/~clark ============================================================================ ================================================================= Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =================================================================
