Exam 2 : lecture Association, Causal Inference & Causality Flashcards
Cause
Precursor event, condition or characteristic required for the occurrence of the disease or outcome
Associations
Relationships between an exposure/ treatment and an outcome/disease
3 types of association (relationships)
Artifacts also (AKA false) Non-causal associations (related but not caused) Causal associations ( one thing cause the other)
Artifactual association
Arise from bias or confounding
Non-causal associations
Disease may CAUSE the exposure
Or
Disease and exposure are both associated with a third factor (confounding) ex: coffee drinking & CHD
Causal associations
Exposure causes outcome
Types of causal relationships
Sufficient cause
Necessary cause
Component cause
Sufficient cause
Cause which precedes a disease, if present, disease with ALWAYS occur
Ex: genetic abnormalities
Can have risk factors (component causes)
Necessary cause
Cause which precedes a disease and has the following relationships:
-cause must be present for disease to occur; cause may also be present without disease occurring
Ex: tuberculosis
NO GAURANTEE OF OUTCOME
Component cause
Risk factors
-if present/active, increases the probability (or likelihood) of disease
Ex: High LDL—
Some patients must be _______________ or ______________ to disease before component cause induce disease (multi factorial)
Primed
Susceptible
Interactions in causal research
Synergism
Parallelism
Synergism
Work together
2 or more components cause such that the combined measure of effect is greater than the sum of the individual effects
(Need BOTH factors)
Parallelism
Either
2 or more components causes such that the measure of effect is greater if either is present
(One or the other will give you the disease)
Hill’s guidelines
Derived following US surgeon Generals 1964 report on smoking
-no hard and fast rule of evidences could be generated by to judge likelihood of causation, but the more you have, the better the causation
Hill’s criteria (guidelines)
Strength Consistency Temporality Biological gradient Plausibility
The higher number of criteria met, when evaluating an association, the ore likely it may be causal. What inference process is this?
Hill’s criteria
Hill’s criteria :
Refers to size of the measure of association (RR/OR/HR)
-the greater the association the more convincing it is that the association might actually be causal
EX: smokers have up to 20 times greater risk of developing lung cancer compared to non-smokers
Strength
T or F
A strong association is neither necessary nor sufficient for causality and weakness of an association is neither necessary nor sufficient for absence of causality
True
Hill’s criteria:
The repeated observations of an association in different populations under different circumstances in different studies
EX: cause-effect relationship between cigarette smoking & CHD greatly strengthened by the fact that a large number of observational studies have consistently demonstrated an INCREASED RISK
Consistency (reproducibility)
Consistency may still obscure the truth, T or F
True
Women’s health study (menopausal hormone therapy)
Hill’s criteria: The cause precede the effect/outcome in time -time-ordered also describable *proximate cause *distal cause EX: 1. take medicine—>projectile vomit Take Medicine for 10 years—
Temporality
Hill’s criteria:
Presence of a gradient of risk (dose response) associated with eh degree of exposure
EX: light smoker are 5 times more likely to develop lung cancer than non-smokers
Heavy smokers are 15 times more likely to develop lung cancer
Biological gradient
Hill’s criteria:
Presence of biological feasibility to the association, which can be understood and explained
EX: infection H. Pylori cause PUD
Plausibility
What is the issue with hill’s criteria “plausibility”
Decision on criterion-based from existing/known beliefs, which may be flawed or imcomplete