Measures of Association

Question 1

Sensitivity

Answer 1

ability of a test to identify those who do have the disease, “true positive”
100% - % sensitivity = % false negative

sensitivity = true positive / (true positive + false negative)

Question 2

Specificity

Answer 2

ability of a test to identify those who do not have the disease, “true negative”
100% - % specificity = % false positive

specificity = true negative / (true negative + false positive)

Question 3

Morbidity - Description Methods

Answer 3

cumulative incidence proportion
incidence rate
prevalence
attack rate

Question 4

Cumulative Incidence Proportion

Answer 4

period of time during which all of the individuals in a population are considered to be at risk for the outcome

Question 5

Incidence Rate

Answer 5

number of NEW cases of a disease that occur during a specified period of time in a population at risk for developing the disease

Question 6

Prevalence

Answer 6

number of affected individuals present in a population at a specific time, divided by the numbers of individuals in the population at that time

Question 7

Attack Rate

Answer 7

number of individuals exposed to something who get the associated outcome, divided by the total number of individuals exposed

Question 8

Risk Ratio

Answer 8

ratio of risk of disease in exposed individuals vs the risk of disease in unexposed individuals

RR = 1 –> risk equivalent between exposed vs. unexposed
RR < 1 –> risk in exposed group is less than the risk in unexposed group
RR > 1 –> risk in exposed group is greater than the risk in unexposed group

Question 9

Odds Ratio

Answer 9

ratio of the probability of occurrence of an event to that of non-occurrence

OR = 1 –> no association
OR < 1 –> exposure decreases odds of disease
OR > 1 –> exposure increases odds of disease

Question 10

RR - Applications

Answer 10

prospective studies
cohort studies

total number of exposed people is available

Question 11

OR - Applications

Answer 11

retrospective studies
case control studies

total number of exposed people is unavailable to calculate RR

Question 12

Attributable Risk

Answer 12

proportion of disease caused by a certain risk factor

risk exposed - risk unexposed

Question 13

Hazard Ratio

Answer 13

the rate at which an unfavorable event occurs

Question 14

Confidence Intervals

Answer 14

numerical range used to describe how reliably study results reflect the entire population

Question 15

Confidence Intervals - Significant

Answer 15

if doesn’t include 0

wide range - low precision
narrow range - high precision (credible values)

Question 16

NNT

Answer 16

number of patients who need to receive treatment for one of them to benefit
low is better

Question 17

NNH

Answer 17

number of patient who receive treatment before one adverse event occurs
high is better