Correlation coefficient

The correlation coefficient $r$ captures how tightly points cluster around a straight line and which way they slope. It runs from $-1$ (perfect negative) through $0$ (no linear association) to $+1$ (perfect positive), so values near $0$ mean a weak linear fit. For example, $r = 0.9$ signals a strong positive linear trend, while $r = -0.2$ signals a weak negative one. Because $r$ only measures linear association, a strong curved pattern can still give an $r$ near 0, and $r$ never establishes causation.