Lecture 9A: Non-Parametric Stat I Flashcards
When should non-parametric statistics be used?
- Categorical data
- Continuous data but criteria for parametric statistics not met (normality, homogeneity of variance)
Non-parametric statistics are typically less powerful than parametric statistics.
What is the Mann-Whitney U Test used for?
Test the difference between 2 independent means
The values for both groups are ranked from smallest to largest.
What does the Modified Ashworth Scale measure?
It measures spasticity levels
Higher scores indicate increased spasticity.
What is the purpose of the Kruskal-Wallis Test?
To determine if there is a difference among three or more groups
Example: baseline FIM bed transfer scores among treatment groups.
What is the Wilcoxon Signed Ranks Test used for?
To compare two related samples
Example: FIM bed transfer scores before and after treatment.
What does the Friedman Test evaluate?
It evaluates differences in repeated measures across three or more time points
Example: knee flexion ROM at pre-test, post-test, and follow-up.
What factors could affect the power of a study when using non-parametric tests?
Small sample size, lack of control group, other confounding factors
Examples include maturation, history, and placebo effects.
What is the relationship between sample size and the ability to detect significant differences in non-parametric tests?
Smaller sample sizes may lead to underpowered studies, reducing the ability to detect significant differences.
What statistical tests are used for analyzing differences when criteria for parametric statistics are not met?
- Mann-Whitney U
- Wilcoxon signed ranks
- Kruskal-Wallis
- Friedman
Also includes Chi-square and McNemar for categorical data.
Which statistical test would be most appropriate for comparing the Barthel Index score (not normally distributed) between patients with Schizophrenia (n=8) and healthy controls (n=8)?
A. Mann-Whitney U test
The Mann-Whitney U test is a non-parametric test used to compare differences between two independent groups.
True or False: The Wilcoxon signed ranks test is suitable for comparing two related samples.
True
This test is used when the same subjects are measured under two different conditions.
Fill in the blank: The _______ test is used to analyze differences in ranks between more than two related groups.
Friedman test
The Friedman test is often used when the assumptions of ANOVA are not met.
What is the appropriate post-hoc test to use after a significant Friedman test result?
C. Wilcoxon-signed ranks test with Bonferroni correction.
This correction is applied to control for Type I errors when multiple comparisons are made.
Which test is not suitable for comparing two independent groups?
D. Kruskal-Wallis test
The Kruskal-Wallis test is used for comparing more than two independent groups.