Causation describes a relationship in which changing one factor produces a change in another. Data analysis often tests apparent relationships, but co-movement alone does not establish causation. section 11.12
Correlation is not causation
Electricity use and an electric bill are positively correlated because greater consumption accompanies a higher bill. Income and private-jet ownership may also move together, but the observed relationship alone does not prove that one measurement causes the other. Use scatter plots and correlation calculations to inspect patterns, then treat causal claims separately. section 11.12
df.corr()
Calculate pairwise correlation to describe co-movement; do not interpret the resulting value as proof of a causal relationship. section 11.12
