Use the Regression tab to run simple linear regressions.
To run linear regressions, your dataset must include at least two variables, and at
least one of the
variables must be numerical.
- Prerequisites
- Select a Dataset
-
Under Settings, select the Explanatory Variable and
Response Variable.
Numerical explanatory variable: A scatter plot is displayed with both a
regression line and confidence bands.
Categorical explanatory variable: A box plot displays the relationship
between the variables.
For both types, two tables are displayed below the plot:
- Model’s Summary Table
- Shows the output for the regression analysis.
- Coefficient Summary Table
- Shows hypothesis test results for each parameter in the regression model.
- Optional:
Adjust the Confidence Interval slider.
The confidence interval value, α, and confidence bands are updated.
- Optional:
Clear Regression Line or Confidence Bands to hide
those from the scatter plot.
- Optional:
Click Scatter Plot of Residuals to see a scatter plot of residuals versus
the x-values.
- Optional:
Click Probability Plot of Residuals to determine the fit
of the regression line.