Explain the Difference Between a Correlation and a Causation in a Real Example

Correlation and causation are explained with the same examples in every statistics resource: ice cream and drowning, shoe size and reading ability. These examples are memorable but useless for evaluating the specific claims that appear in health, psychology, and social science research. This explains the distinction using a real relationship you care about, names the confounders, tells you what the evidence actually shows, and separates the honest finding from the popular version.

I want to understand the difference between correlation and causation, using a real example I care about.

The relationship I want to understand: {RELATIONSHIP_EXAMPLE} [for example: 'exercise and mental health', 'sleep and productivity', 'screen time and wellbeing in children']

Explain:
1. What correlation means in this specific example: what the data actually shows, stated without the causal implication
2. What would have to be true for this to be causal: the conditions under which we could say X actually causes Y, not just appears with it
3. The most plausible confounders: the [two or three] third factors that might explain both X and Y appearing together without either causing the other
4. What the evidence actually shows: whether, for this specific relationship, scientists have established causation, established strong correlation with plausible mechanism, or have only correlation
5. The practical implication: what the honest evidence tells you to do or believe, as opposed to what the popular version of this finding suggests