Lesson 5: Continuous Outcomes, Between Groups Differences

Question 1

One Sample t-test

Answer 1

A test that compares the mean score of a sample to a known value, typically the population mean

Question 2

Independent Samples t-test

Answer 2

A test to determine the probability that the difference in two groups happened by chance. AKA student t-test or two sample t-test

Question 3

Mann-Whitney

Answer 3

The non-parametric equivalent of the student t-test (used for skewed or ordinal data &/or or small sample sizes)

Question 4

Paired T-test

Answer 4

A test that examines the difference between paired values in two samples (ex: pre and post test)

Question 5

Wilcoxon Matched-Pair test

Answer 5

The non-parametric equivalent of the paired t-test (used for skewed or ordinal data &/or or small sample sizes)

Question 6

Analysis of Variance (ANOVA)

Answer 6

A test to determine the probability that the difference in three or more group means happened by chance

Question 7

Kruskal Wallis One-Way ANOVA

Answer 7

The non-parametric equivalent of ANOVA

Question 8

Bonferonni Correction

Answer 8

An approach to reducing the statistical significance level when multiple comparisons are made on the same set of data (adjusts for multiple comparisons by dividing alpha by the # comparisons made)

Question 9

A one sample t-test compares..

Answer 9

A single sample mean to the population mean

Question 10

An independent t-test compares..

Answer 10

the means of two INDEPENDENT samples to see if the difference between the two may have occured by chance

Question 11

What can a post-hoc test tell us?

Answer 11

Post-hoc can identify which means are significantly different from each other after an ANOVA

Question 12

Repeated Measures ANOVA..

Answer 12

compares the means of THREE or more dependent samples (ex: comparing the mean outcome of a group at 4 separate points in time)

Question 13

What test would you use to examine the difference between three or more groups for a categorical outcome variable?

Answer 13

Chi-square should be used to compare groups on categorical outcomes. T-test and ANOVA are used for continuous outcomes.

Question 14

Which test would you use to examine how three or more groups differ for a continuous outcome variable?

Answer 14

ANOVA

Question 15

What do we do if we have n<30 but the data is still normal?

Answer 15

Even with a small data set, if the data is normal we can still use parametric tests.

Question 16

Name two common types of paired t-test data types.

Answer 16

1. Same individual in both groups (time based or matched sample [healthy tissue, diseased tissue]
2. Matched Individuals