Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
25 Cards in this Set
- Front
- Back
DEFINE:
Confounding |
Refers to effect of an extraneous varibale that wholly or partially accounts for the apparent effect of the study exposure, or that masks an underlying true association
-so association between exposure, disease could be due to another variable |
|
Confounder is also known as ____.
|
third variable
|
|
Confounder is a _____ for the diseaase, even among the _____.
|
risk factor, unexposed
|
|
Confounder is associated with the ____ in the ____ population.
|
exposure, source
|
|
Confounder [is/is not] an intermediate factor in the casual pathway from exposure to disease
|
is not
|
|
It is important that the confounder is related to both the _____ and ____
|
disease, exposure
|
|
It is important that the confounder variable [is/is not] on the casual pathway.
|
is not
|
|
Confounding can be considered as a type of ____
|
bias
|
|
Confounding will introduce bias into ____ ____, ____ validity of p values and confidence intervals.
|
point estimate, reduce
|
|
If potential confounding factor is ______ associated with both exposure and disease, then it will result in overestimate of true association.
|
positively
|
|
If the potential confounding factor is positively associated iwth both E and D, then it will result in _____ of the true association.
|
overestimate
|
|
If confounding factor is ___ associated iwth E and D, then will result in overestimate of true association.
|
negatively
|
|
If confounding factor is negatively associated with E and D, then will result in ____ of true association.
|
overestimate
|
|
If the potential confounding factor is _____ associated with exposure AND _____ associated with disease (or vice versa), failure to control for it will result in an underestimate of the true association
|
negatively, positively
|
|
If the potential confounding factor is negatively associated with exposure and positively associated with disease (or vice versa), failure to control for it will result in an _____ of the true association
|
underestimate
|
|
Name 3 different methods for identifying confounding
|
1. Quick Triangle Approach
2. Data-based 3. Theory-based |
|
What is the data-based method that identifies confounding?
|
Compares crude and adjusted estimates
|
|
What is the theory based method for identifying confounding?
|
-looks at relationships among E, D, and CF
-more formal than quick triangle approach |
|
What are 3 criteria that must be met in order to use the theory based method to identify confounding?
|
1. must be associated with E
2. must be an independent risk factor for D 3. must not be an intermediate step in the causal pathway between E and D |
|
What are 3 criteria that must be met in order to use the theory based method to identify confounding for cohort studies with count denominators?
|
Potential confounder must be associated with the exposure
Potential confounder must be an independent risk factor for disease among the unexposed Potential confounder must not be on causal pathway |
|
What the the 3 criteria that must be met to identify confounding factors using the theory based mthod for a CaCo study?
|
Potential confounder must be associated with the exposure among controls
Potential confounder must be an independent risk factor for disease among the unexposed Potential confounder must not be on causal pathway |
|
Which theory used to identify confounding factor is more accurate?
|
Theory-based
|
|
Which theory used to identify confounding factor is more simple and commonly used?
|
data based
|
|
In the design stage, how do you control for confounding?
|
1. Randomization
2. Restriction 3. Matching |
|
In the analysis stage, how do you control for confounding?
|
1. Stratified analysis
2. mathematical modeling |