Relationship Relation: Association: real and spurious Statistical: Correlation: harmonic Causation
Causation: -direct factor outcome -indirect factor outcome Types of causal relationship: 1- factor is necessary and sufficient (rare), ex.; agent host A outcome
2- factor is necessary but not sufficient: A+B+C outcome 3-factor is not necessary but sufficient: A B C outcome or or
4- neither necessary nor sufficient: A + B + C D + E + F outcome or
A B A + B C A B + C A B C A B A B C C
Systematic error (bias) Confounders Before starting to prove causation, We should Identify and evaluate the effects of: Random Error (chance) Systematic error (bias) Confounders
Conditions for a relationship to be causal: 1- Strength of the association 2- Temporal relationship 3- Dose response relationship 4- Replication of results 5- Biological plausibility
Others: 1- Specificity 2- Consistency 3- Presence of alternative hypothesis 4- Cessation of exposure