Research 2: Tests of Difference

Question 1

parametric data

Answer 1

• continuous data only

- normal distribution of data in both groups

Question 2

non-parametric data

Answer 2

• categorical or continuous data that is not normal

Question 3

t-test

Answer 3

• collected from 2 independent samples that differ significantly
• ex: experimental and control group

Question 4

paired t-test

Answer 4

• collected from the same sample that differ significantly

- ex: height and weight from same subject

Question 5

ANOVA

Answer 5

• overall test of whether multiple (>3) group means differ

Question 6

Repeated ANOVA

Answer 6

• ANOVA for data that has been measured repeatedly on the same subject
• paired data set
• ex: height and weight on more than 3 subjects

Question 7

Factorial ANOVA (n-wat ANOVA)

Answer 7

• when continuous outcome has been measured with multiple factors to test SYNERGISTIC effects
• ex: Patients’ level of chronic low back pain was measured hypothesizing that the two factors, treatment 1 and treatment 2, together would have synergistic effect of lessening the pain

Question 8

Mixed ANOVA

Answer 8

• when a continuous outcome has been measured with multiple groups repeatedly over time
• ex: Patients’ quality of life associated with their chronic low back pain was measured repeatedly (at baseline, 3 months, 6 months) hypothesizing that the factor, treatment 1, would have effect of improving their quality of life associated with low back pain

Question 9

Analysis of Covariance (ANCOVA)

Answer 9

• when a continuous outcome has been measured with a confounding variable for the purpose of adjusting for the confounder
• to control for factors that can not be randomized
• ex: You might want to find out if a new drug works for depression. The study has 3 treatment groups and 1 control group.
  A regular ANOVA tell you if the treatment works.
  ANCOVA can control for other factors that might influence the outcome.
  For example: family life, job status, or drug use.

Question 10

Mann-Whitney U Test

Answer 10

• non-parametric t-test

- 2 independent samples that differ significantly

Question 11

Wilcoxen Signed-Rank Test

Answer 11

• non-parametric t-test

- 2 means from same sample

Question 12

Kruskal-Walls H Test

Answer 12

• non-parametric ANOVA

- test mean difference between >3 independent groups

Question 13

Friedman Test

Answer 13

• non-parametric repeated ANOVA

- test mean difference between >3 related groups