Lecture 54 - Epidemiology 6

Question 1

what are the 2 broad types of error in epidemiologic studies

Answer 1

1. systematic error/bias
2. random error

Question 2

what are the 3 types of bias

Answer 2

1. selection bias
2. information bias
3. confounding bias

Question 3

internal validity

Answer 3

validity of the inferences drawn as they pertain to the members of the source population

Question 4

external validity

Answer 4

validity of the inferences drawn as they pertain to individuals outside the source population

Question 5

how can random error be reduced

Answer 5

1. increase sample size
2. increase precision measurements in the study (replication)

Question 6

type II error

Answer 6

false negative
study results show no association while there is one in reality; null accepted but false

Question 7

type I error

Answer 7

false positive
study results show association while there is none in reality; null rejected but its true

Question 8

if the p-value is less than the alpha level then the null hypothesis is _____

Answer 8

rejected

Question 9

alpha level

Answer 9

a fixed cut-off

Question 10

p-value

Answer 10

continuous measure, computed from the data, of the compatibility between a hypothesis and the data

Question 11

study conclusions can be influenced by

Answer 11

1. sample size
2. variability and precision of measurements

Question 12

narrow confidence interval

Answer 12

less variability and higher precision in the estimate

Question 13

wide confidence interval

Answer 13

large amount of variability or imprecision in estimate

Question 14

what can a confidence interval tell you

Answer 14

1. direction and magnitude of underlying association
2. random variability of point estimate