Biostatistics

Question 1

SEM

Answer 1

Standard Error of the Mean
Calculation: SEM = SD / sqrt (sample size)
In any normal distribution, 95% of the sample means lie within +/- 2 SEM of the population mean

Question 2

95% CI

Answer 2

Mean +/- 1.96 x SEM

*95% certainty that the true mean of the entire population studied will be within this interval

Question 3

CI for continuous variables vs OR/RR

Answer 3

If continuous: NS if contains 0;

If OR/RR: NS if contains 1

Question 4

Nondirectional: Difference Hypothesis Testing

Answer 4

Traditional 2-sided t-test

Confidence intervals

Question 5

Nondirectional: Equivalence Hypothesis Testing

Answer 5

Two 1-sided t-test (TOST) procedure

Confidence intervals

Question 6

Directional: Superiority Testing

Answer 6

Traditional 1-sided t-test

Confidence intervals

Question 7

Directional: Noninferiority Testing

Answer 7

Confidence intervals

Question 8

Student unpaired t-test

Answer 8

Parametric, 2 independent samples/groups, continuous data

group 1 vs group 2

Question 9

Student paired t-test

Answer 9

Parametric, 2 paired/matched samples, continuous data

group 1: measurement 1 vs measurement 2

Question 10

One-way ANOVA

Answer 10

Parametric, 3 or more independent samples/groups, continuous data
(group 1 vs group 2 vs group 3)

Question 11

Two-way ANOVA

Answer 11

Parametric, 3 or more independent samples/groups + an additional factor added, continuous data
(young groups: group 1 vs group 2 vs group 3
old groups: group 1 vs group 2 vs group 3)

Question 12

Repeated-measures ANOVA

Answer 12

Parametric, 3 or more matched samples (not independent), continuous data
(Group 1: measurement 1 vs measurement 2 vs measurement 3)

Question 13

Post-Hoc ANOVA tests

Answer 13

Determine which ANOVA groups actually differ from each other

Turkey HSD, Bonferroni, Scheffé, Newman-Keuls

Question 14

ANCOVA

Answer 14

Parametric, provides a method to explain influence of a categorical (independent variable) on a continuous variable (dependent variable) while statistically controlling for other variables (confounding)

Question 15

Wilcoxon rank sum, Mann-Whitney U test, Wilcoxon Mann-Whitney Test

Answer 15

Nonparametric, 2 independent samples (related to t-test), ordinal data

Question 16

Kruskal-Wallis one-way ANOVA by ranks

Answer 16

Nonparametric, 3 or more independent groups (related to one-way ANOVA), ordinal data

Question 17

Sign test and Wilcoxon signed-rank test

Answer 17

Nonparametric, 2 matched/paired samples (related to paired t-test), ordinal data

Question 18

Friedman ANOVA by ranks

Answer 18

Nonparametric, 3 or more matched/paired groups, ordinal data

Question 19

Chi-square test

Answer 19

2 independent groups, Nominal data

Question 20

Fisher exact test

Answer 20

2 independent groups, Nominal data

*specialized version of chi-square test for small groups (cells) containing less than 5 predicted observations

Question 21

McNemar

Answer 21

2 paired/related samples, Nominal data

Question 22

Mantel-Haenszel

Answer 22

Nominal data, controls for the influence of confounders

Question 23

Pearson Correlation

Answer 23

Strength of relationship of 2 variables (normally distributed continuous data)

Question 24

Spearman Rank Correlation

Answer 24

Strength of relationship of 2 variables (ordinal data or nonparametric continuous data)

Question 25

Simple linear regression

Answer 25

1 continuous independent variable, 1 continuous dependent variable

Question 26

Multiple linear regression

Answer 26

1 continuous independent variable, 2 or more continuous dependent variables

Question 27

Simple logistic regression

Answer 27

1 categorical response (dependent) variable and 1 continuous/categorical explanatory (independent) variable

Question 28

Multiple logistic regression

Answer 28

1 categorical response (dependent) variable and 2 or more continuous/categorical explanatory (independent) variable

Question 29

Nonlinear regression

Answer 29

variables are not linearly related

Question 30

Polynomial regression

Answer 30

any number of response and continuous variables with a curvilinear relationship (cubed, squared)

Question 31

Cochran Q

Answer 31

2 or more paired/matched samples, nominal data