Measures of Association Flashcards
What are measures of association?
Provide a mathematical assessment of the relationship between a given exposure and the outcome of interest
What two things do measures of association do?
- determine if there is an association
- measure the strength of association
**these are used in analytical studies
What would you expect a positive and negative association to be when comparing EXPOSURE groups?
Positive = more dz is found in a group of subjects that has the exposure than in a group of subjects that doesn’t have exposure
Negative = LESS dz is found in a group of subjects that has the exposure than in a group of subjects that doesn’t have exposure
What would you expect a positive and negative association to be when comparing OUTCOME groups?
Positive = MORE of the exposure is found in a group of diseased subjects than in a group on non diseased subjects
Negative = LESS of the exposure is found in a group of diseased subjects than in a group of non diseased subjects
We assume that the exposure is NOT associated with the disease if…..
When comparing exposure groups: the same amount of dz is found in a group of subjects that has the exposure and a group that hasn’t
When comparing outcome groups: the same amount of the exposure is found in a group of diseased subjects as the group of non diseased subjects
Measures of associations are used to make what two comparisons?
- compare exposure groups: compare the number of animals with the outcome in each exposure group
- Compare outcome groups: compare the number of animals with exposure in each outcome group
Since the number of subjects in our study groups are almost never the same, we use measures of disease occurrence; ________, _______, and odds to calculate measures of association
prevalence
incidence (risk)
When comparing exposure in outcome groups (diseased vs non diseased), in retrospective studies, what measure of association will be used?
Odds ratio
for cross sectional studies and case control studies
When comparing outcomes in exposure groups (exposed vs non exposed), what measure of association is used for prospective studies, and what measure of association is used for retrospective studies?
Prospective: Relative risk (incidence ratio), and Attributable risk – used for prospective cohort studies and clinical trials
Retrospective: Prevalence ratio - used for retrospective cohort studies and cross sectional studies
T/F: In case control and cross sectional studies, the exposure and disease have already occurred when the study begins
TRUE
this means you can not measure incidence (new cases)
Case control studies cannot estimate _______ in the population, but they can determine the _________ between exposure and disease
cannot estimate PREVALENCE
can determine ASSOCIATION
Cross sectional studies estimate the prevalence, but can also evaluate _________
Exposures
if exposure data are collected as part of the study
_____ is used to measure exposure in the diseased and non-diseased groups
Odds
Odds is the ration of the number exposed to the number not exposed
Ex: if there were 10 diseased animals and 3 of them were exposed –> the odds of exposure in the diseased group would be 3/7
What is the odds ratio?
The ratio of the odds of exposure in the diseased group to the odds of exposure in the non diseased group
Offs of exposure in the dx group/odds of exposure in non dz group
How is the odds ration interpreted?
Example:
The odds of being exposed was ____ times higher in the diseased animals that in non diseased animals
If OR = 1: odds of exposure among cases was equal to that of controls (no association)
If OR is greater than one: POSITIVE association (odds of exposure among cases was greater than controls)
If OR is less than one: NEGATIVE association (odds of exposure among cases was less than controls)
The odds ration will tell you if there is an association, and the _____ of the association
Magnitude/strength
*know how to calculate the odds ratio
______ is the measure used to compare the amount of disease that occurs in the exposed and unexposed groups in prospective studies
Incidence = risk
What is cumulative incidence?
aka attack rate
number of new cases at the end of a study divided by the population at risk at the beginning of the study. (think outbreak)
Ex: 10 healthy exposed animals and 3 of them developed dx during the study –> the risk of dz in the exposed group during the study would be 3/10
What is the incidence rate?
Number of new cases at the end of a study divided by the animal-time at risk.
Ex: if there were 10 healthy animals exposed for 20 months each and 3 of them developed dz:
the incidence rater in the exposed group would be 3/200 animal-months
______ risk is used to compare the risk (or incidence) of disease that occurs in the exposed and unexposed groups
Relative risk
incidence of disease in the exposed group / incidence of disease in the unexposed group
How is the relative risk (RR) interpreted?
If RR = one: the risk of disease in the exposed group is equal to the risk of the unexposed group
If the RR is greater than one: POSITIVE association - the risk of dz in the exposed group is greater than the unexposed
If the RR is less than one: NEGATIVE association - the risk of dz in the exposed group is less than the risk in the unexposed group
*know how to calculate this
What is the attributable risk (AR)?
Amount or proportion of overall disease incidence in a population or group that can be attributed to a specific exposure.
Results are interpreted: “ ____% of the overall disease incidence can be attributed to this particular exposure”
T/F: Attributable risk is used to quantify an association in epidemiological studies
FALSE
- typically not
- it is mostly used to set priorities in disease control programs
- know how to calculate AR
What measure of association is used in retrospective studies?
Prevalence ratio
used in retrospective cohorts and cross sectional studies
________ is the measure used to compare the amount of disease that occurred in the exposed and unexposed groups in retrospective studies
Prevalence
*prevalence is used because the disease has already occurred when the study has begun
= the probability of being diseased: The number of diseased divided by the total number exposed
How do you calculate and interpret the PR (Prevalence ratio)
PR = prevalence of dz in exposed / prevalence of dz in unexposed
Ex: The prevalence of dz was __ times as high in exposed animals as in unexposed animals”
PR = 1 : no association; prevalence in both groups is equal
PR greater than one = Positive association (possibly causal) - prevalence of the dz in exposed group was equal to the prev. in unexposed
PR less than one = Negative association (possibly protective) - the prev in dz in the exposed group was less than the prev in the unexposed group
