Comparison Of Outcome Variables Flashcards
Parametric tests are used when:
- There is independence between variables
- Values take on a normal distribution
- Homogenous variances e.g. equal variances between individual grps
Parametric T-test is used when..
There are 2 groups.
The 3 types:
1. 1 sample t-test: comparing the average of one group against the established, set average
2. 2 sample t-test: comparing the averages of 2 separate groups
3. Paired T-test: 2 groups measured at 2 separate instances
Parametric ANOVA is used when..
There are more than 2 groups to be tested
Non-parametric tests are used when..
- Data is ordinal (has a scale)
- Asymmetric distribution (e.g. presence of outliers)
- Heterogenous variances (e.g. values have wonky intervals)
What are the non-parametric T-test equivalents?1
- Single-sample Wilcoxon test (1-sample t-test)
- Mann Whitney U test/Wilcoxon’s rank sum test (2-sample t-test)
- Wilcoxon’s signed rank test (paired t-test)
- Kruskal-Wallis analysis of variance, >2grps (ANOVA)
Hypothesis testing. What is your null and alternative hypothesis?
Null hypothesis, Ho: there is no difference between the groups
Alternative hypothesis, H1: there is a difference between groups
What does the P-value tell u in hypothesis testing?
P-value: the probability of the occurrence of a given event
- p-value>0.05: accept null hypothesis, there is no difference between the groups
- p-value<0.05: reject null hypothesis, there is a difference between groups
One sample kolmogorov smirnov test is a..
One sample t test
Wilcoxon rank sum test is a
Two sample t test
(X=Y)
Mann whitney test is a
Two sample t-test (X>Y)
Wilcoxon signed rank test is a
Paired t test
Non parametric equivalent of 1 sample t test is..
1 sample wilcoxon signed rank test
Non-parametric equivalent of 2-sample unpaired t-test is..
Wilcoxon test
Non-parametric equivalent of 2-sample paired t-test is..
Mann whitney
Non-parametric equivalent of 1 way ANOVA is..
Kruskal-willis test