The purpose of this article is to explain how to set up Group Comparison (ANOVA)
Purpose
The purpose of the Group Comparison (ANOVA) is to compare the performance of groups using a numeric variable.
Limitations
- Can only run one group and one value column at a time
Steps to Run
- Go to the Tools menu
- Select the Data Science option
- Select the Group Comparison (ANOVA) option
- Enter the data table, the Group column, the Value column and check whether or not to include pairwise comparisons.
Group Comparison Inputs
- Data table - Choose your data table for this analysis.
- Group column - The group column should be a categorical variable, such as Operator
- Value column - The value column should be a continuous variable, such as EUR
- Checkbox to include or exclude pairwise comparisons. If the box is not checked, the 'Pairwise comparisons between each group' output table will not be generated
Outputs:
- If pairwise comparisons are included, there are four outputs
- Pairwise Comparisons between each Group table
- ANOVA and Kruskal-Wallis Test for Groups table
- Group Results table, including normality checks on each group name
- Box plot visualization
How to filter a subset of data
- Open the filter panel by clicking the filter icon on the top bar.
- Choose the correct filtering scheme
- Click " Refresh data table" on the visualization.
- This syncs with all the other visualization on the Group comparison (ANOVA)
- Note: Try selecting and filtering to on the previous visualization then open up Group Comparison (ANOVA)
See RAI Group Comparison (ANOVA) video for an explanation of how to interpret the value.
Data Science Toolkit: Group Comparison (ANOVA) from Ruths.ai on Vimeo.
For additional information on RAI Data Science Toolkit documentation, click here.