Critical appraisal

Question 1

Confounder

Answer 1

variable associated with both exposure and outcome

Question 2

Best type of study design to minimize effects of confounders

Answer 2

RCT

Question 3

Cons of doing RCT

Answer 3

Expensive, time consuming, difficult for rare events

Question 4

how to calculate relative risk

Answer 4

incidence of intervention / incidence of control

Question 5

Relative risk reduction

Answer 5

ARR = (risk in intervention - risk in control)
divided by
risk in control group
(or 1-RR)

Question 6

case control studies

Answer 6

identify groups based on a specific OUTCOME, see if they have certain exposures

Question 7

cohort studies

Answer 7

follow subjects with a specific EXPOSURE and evaluate outcomes, exposure not under investigator’s control

Question 8

best method to study rare diseases

Answer 8

case control (go back and look at their history)

Question 9

sensitivity

Answer 9

given that the disease is present, the probability that the test is positive

Question 10

specificity

Answer 10

given that the disease is absent, the probability that the test is negative

Question 11

sensitivity (equation)

Answer 11

TP/(TP+FN)

Question 12

specificity (equation)

Answer 12

TN/(TN+FP)

Question 13

positive predictive value

Answer 13

given that the test is positive, the probability that the disease is present

Question 14

negative predictive value

Answer 14

given that the test is negative, the probability that the disease is absent

Question 15

PPV and NPV vary with…

Answer 15

disease prevalence

Question 16

PPV (equation)

Answer 16

TP/(TP+FP)

Question 17

NPV (equation)

Answer 17

TN/(TN+FN)

Question 18

Power of a study (equation)

Answer 18

1 - Type II error (the chance that the p value will not be statistically significant despite a true difference between the two groups)

Question 19

Type 1 error

Answer 19

the probability that the difference observed is due to chance

Question 20

p-value (definition)

Answer 20

the probability that the difference observed in the study is simply due to chance (type 1 error)

Question 21

LR for a positive test

Answer 21

sensitivity/(1-specificity)

Question 22

LR for a negative test

Answer 22

(1-sensitivity)/specificity