Statistics - Correlation does not imply causation

1 - About

Correlation does not imply causation

Studies have shown that people who have more birthdays live longer.

3 - Example

3.1 - Eating ice cream

In the late 1940s, public health experts recommended that people stop eating ice cream as part of an anti-polio diet. It turned out however that there was only a correlation between polio incidence and ice-cream consumption, because outbreaks were most common in the summer.

3.2 - Seven Countries Study

Seven Countries Study shows a correlation between the fat calories consumed and deaths per 1,000 from degenerative heart disease.

The experiment failed to consider other factors that might cause deaths from degenerative heart disease.

It appears in this study that there's a correlation between per capital annual sugar consumption in pounds, and deaths per 1,000 of degenerative heart disease.

Including additional data or factors would have likely led Ancel Keys to a different conclusion.

3.3 - Facebook vs princeton

Debunking Princeton “we are even more concerned about the fate of the planet, because Google Trends for 'air' have also been climbing steadily, and our projection show that by the year 2060, there we know air left at all.”

vs Princeton: Epidemiological modeling of online social network dynamic (John Cannarella, Joshua A. Spechler)

data_mining/correlation_does_not_imply_causation.txt · Last modified: 2015/06/07 14:35 by gerardnico