CAUSAL INFERENCE Flashcards
(53 cards)
statistical dependence between two variables
Statistical Association
either positive or negative
Statistical Association
process of using statistical methods to characterize the association between variables.
Statistical Association
process of ascribing causal relationships to associations between variables
Causal Inference
Types of Association
- Causal
- Noncausal
types of causal
- Direct
- Indirect
Alteration in the frequency or quality of one event is followed by a change in the other
causal
Association is a result of the relationship of both factor and disease with a third variable
non-causal
Factor that plays an essential role in producing an outcome
cause
alteration if factor A is directly related to change in factor B
direct causal
there is another factor that is associated with the chnage of outcome
indirect causal
presence of mechanism that leads from exposure to disease
cause
Identifiable relationship
between exposure and
disease
association
Process of Causal Inference:
- Determine the validity of the association
- Determine if observed association is causal
rule out chance, bias, confounding as explanation of the observed association
Determine the validity of the association
consider totality of evidence taken from a number of
sources
Determine if observed association is causal
2 types of validity:
- internal
- external
- Validity within the study
- Estimate of effect measure is accurate
- Not due to systematic error
internal validity
- Validity beyond the study
- Estimate generalizable to bigger population
- Not due to random error
external validity
Goal of Epidemiologic Studies
to estimate the value of the parameter with little error
Sources of errors:
- random errors
- systematic errors
because of sampling errors, chance
random errors
because of biases and confounding
systematic errors
difference between population value of parameter being investigated and the estimate value based on the different samples
random errors
