Biostatistics

Question 1

Odds of an event

Answer 1

probability of the event / (1 - probability of the event)

Question 2

Odds ratio

Answer 2

measure of association between an exposure and an outcome

2x2 table calculation –> OR = ad/bc

Question 3

Relative risk

Answer 3

risk of disease in the exposed divided by the risk of disease in non-exposed

RR = [a/(a+b)] / [c/(c+d)]

Question 4

effect modification

Answer 4

external variable positively or negatively impacts the observed effect of a risk factor on disease status

but there has to be a significant difference in the RR when accounting for the external variable via stratified analysis

*first test

Question 5

observer bias and measurement bias

Answer 5

distort strength of an association by misclassifying exposed/unexposed and/or diseased/nondiseased subjects

Question 6

Recall bias

Answer 6

inaccurate recall of past exposure by people in the study

mostly with retrospective studies like case-control studies

Question 7

case control study

Answer 7

investigator knows what the disease process is but is retrospectively trying to determine what the exposure or risk factor was

Question 8

Analysis of Variance (ANOVA)

Answer 8

used to determine whether there are significant differences between the means of 2 or more independent groups

e.g. relationship of smoking different amounts (heavy, light, not at all) and FEF

small difference btwn means = accept null hypothesis
large difference = reject null hypothesis

Question 9

Chi-square tests

Answer 9

checks association between 2 categorical variables

Question 10

Multiple linear regression

Answer 10

models linear relationship between a dependent variable and 2 or more independent variables

counterpart = Pearson correlation coefficient

Question 11

Pearson correlation coefficient

Answer 11

measures strength and direction of a linear relationship between 2 variables

Question 12

Two-sample t-test

Answer 12

used when 2 groups are compared

equivalent of ANOVA