Measures of Association
Odds versus Risk
Significance
Power and Error
Evaluating diagnostic tests
100
The number of people who need to receive a treatment in order to avoid one disease event?
What is number needed to treat?
100
A ratio of probabilities
What is relative risk?
100
The hypothesis that there is a difference in outcome in the exposed versus the unexposed.
What is the alternative hypothesis?
100
The risk of finding a false negative result
What is Type 2 error?
100
1 minus probability that a test yields a false positive
What is specificity?
200
The risk in the exposed minus risk in the unexposed.
What is risk difference?
200
Odds of disease/1+odds of disease
What is probability of disease?
200
The hypothesis that there is no difference in outcome between the exposed and unexposed.
What is the null hypothesis?
200
The risk of finding a false positive result
What is Type 1 error?
200
The probability of person with disease having positive test divided by the probability of person without disease having a positive test
What is the positive likelihood ratio?
300
The ratio of risk in the exposed to risk in the unexposed
What is the relative risk?
300
Probability of disease/1-probability of disease
What is the odds of disease?
300
The probability of obtaining your results if the null hypothesis is true.
What is the p value?
300
A study's ability to detect a true difference.
What is power?
300
The chance that a person has the disease given a positive test result.
What is the positive predictive value of a test?
400
The odds of exposure in the diseased divided by the odds of exposure in the disease free.
What is the exposure odds ratio?
400
Appropriate measures of risk when the exposure is common.
What is relative risk and absolute risk?
400
The range of values in which the true value is likely to be found 95% of the time.
What is the 95% confidence interval?
400
The minimum acceptable chance that a study fails to reject the null hypothesis.
What is 20%?
400
The probability that a randomly selected "diseased" person would have a higher value of the test than a randomly selected "non-diseased" person, i.e. the accuracy of a test?
What is the area under an ROC curve?
500
1/(Risk Difference)
What is number needed to treat?
500
Appropriate measures of risk when the exposure is rare?
What is relative risk, absolute risk and odds ratio?
500
The most useful test for judging both the significance and stability of your estimated association.
What is the 95% confidence interval?
500
The minimum acceptable chance that a study rejects the null hypothesis when it is actually true?
What is 5%?
500
A measure of test performance that depends on the prevalence of a disease.
What is the positive or negative predictive value of a test?
M
e
n
u