A negative correlation is a relationship in which one variable increases as the other decreases. The two variables move in opposite directions.

As the number of hours spent watching television rises, school grades may fall; as outdoor temperature drops, heating costs rise. The strength of the relationship is expressed by a correlation coefficient that ranges from 0 to -1.00. A coefficient of -0.80 indicates a strong negative relationship; a coefficient of -0.20 indicates a weak one. Scatterplots of negatively correlated data slope downward from left to right.

Negative correlation does not imply that one variable causes the other to change. A third factor may influence both, or the direction of influence may be the reverse of what is assumed. Correlational designs identify associations; experimental designs are required to test causal claims.

When two measures systematically move in opposite directions, the relationship is a negative correlation.