Reading...
Play button
Play button
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;
17 Cards in this Set
- Front
- Back
|
Definition of Case-Control Study
|
compares cases and controls with respect to their level of exposure to risk factor (often uses odds ratio to compare between groups)
|
|
|
Definition of case-based case-control study
|
study in which incident cases are identified as individuals are diagnosed
|
|
|
Selection Bias
|
when cases and controls are not selected from the same (or even similar) reference populations
|
|
|
Definition of Nested Case-Control (i.e. Case-Cohort) Studies
|
Case-control study within a cohort study
|
|
|
Incidence Density Sampling (i.e. risk set sampling)
|
cases are compared with cohort members who are at risk at the time that the case occurs. This way, cases occurring later in the follow-up are eligible to be controls for earlier cases.
|
|
|
Over-matching
|
Matching Cases and controls on non-confounding variables
|
|
|
Frequency matching
|
selecting a control group so as to balance the distributions of the matching variable (without doing individual case-by-case matching)
|
|
|
Another type of matching:
minimum Euclidean distance measure method |
the closest dots on the graph (case, control) are matched.
|
|
|
Advantages of Matching (3)
|
1. control for some confounding
2. increases statistical power 3. logistically straight-forward way to get a comparison group |
|
|
Disadvantages to Matching (6)
|
1. difficult or impossible sometimes
2. the association between the matching variable and outcome can't be assessed anymore because set equal 3. cannot assess additive interaction between matched variables and exposures 4. increases internal validity (comparability), decreases external validity (representativeness) 5. matching cannot be undone, avoid overmatching 6. if the matching variables are only weak confounders then no statistical power is gained |
|
|
Residual Confounding
|
residual differences between cases and controls (e.g. matched on broad age category, but average still very different)
|
|
|
Definition of "Odds"
|
Odds is the ratio of the probability of an event of interest to that of the non-event (p/q)
|
|
|
Formula of Incidence Odds
|
q/1-q
|
|
|
Point Prevalence Odds
|
Point Prevalence/ 1- Point Prevalence
|
|
|
Odds ratio allows for the estimation of what in case-control studies?
|
Relative Risk (apparently easier to understand than odds)
|
|
|
Another term for cross-product ratio?
|
Odds Ratio
|
|
|
Definition of Case-Crossover Study
|
study in which two or more interventions are compared, where each case is also his/her own control
|
