A Question of Causation (Program 11)

Determining cause and effect relationships:
1. Analyzing Association
2. Simpson's paradox
3. Causation
Ice cream sales vs number of drownings
Speed limit vs number of deaths-confounding
Population of Louisiana and shrinkage of the state-coincidence
Lurking variables:
- Sex discrimination at 'City University'-Simpson's Paradox
  - discussed the need for quantitative variables to calculate correlation, as opposed to qualitative variables, as in this paradox
- Lung cancer and smoking
  - retrospective studies
  - prospective studies: both comparing smokers and non smokers
Criteria for Causality - Consistency of the association
- Strength of the association
- Specificity of the association
- Temporal Relationship of the association
- Coherence of the association
Idea: Conduct experiments