Question

Using a BA example, provide an explanation as to why correlation does not equal causation.

Answer 1

Correlation is not necessary causation because the correlation may be spurious.

Sometimes two variables appear to be highly correlation but in reality they are not correlated. Mainly this happens because of an unseen variable that was not apparent at the time of examination.

Let's say for example that in a scatter plot of ice cream sales and shark attacks on a beach, there was seen to be a high degree of correlation. But it does not imply causation because the two variables do not make any sense of association. However, the cause of such correlation could be a third variable which can be taken as "good weather" with lots of people at the beach both having ice cream and enjoying the swim at the sea.

Correlation does not equal causation mainly in cases of large sample sizes because lots of uncorrelated random variables may have high sample correlation in high dimensions or large sample sizes.