Epi/Biostats Flashcards
1
Q
RR
A
cohort studies (exposure vs. no exposure)
a/(a+b))/(c/(c+d)
2
Q
AR
A
risk in exposed - risk in unexposed
a/(a+b) - c/(c+d)
3
Q
RRR
A
1-RR
4
Q
NNT, NNH
A
NNT = 1/ARR
NNH = 1/AR
5
Q
Reliability, aka
A
precision
6
Q
Validity, aka
A
Accuracy
7
Q
Berkson bias
A
study populations selected from hospital is less healthy than general population
8
Q
OR
A
case-control (disease vs no disease)
a/c) / (b/d
9
Q
Type I error vs Type II error
A
Type I = false positive, rate = alpha
Type II = false negative, rate = beta
10
Q
Power
A
frequency of TP
= 1 - beta (ie 5% FN rate means you miss 5% of the true positives and have a true positive rate of 95%)
