Specify the default settings for Discover Best Model (Continuous Response)

File > Options > Predictive Analytics > Discover Best Model (Continuous Response)

Specify the default methods for Discover Best Model (Continuous Response). The changes you make to the defaults remain until you change them again, even after you exit Minitab.

Criterion for selecting the best model

Choose the criterion to determine the best type of model. You can compare the results from several methods to determine the best choice for your application.

Maximum R-squared
The maximum R2 method works well across many applications. This method minimizes the sum of the squared errors.
Use Huber loss function to fit TreeNet® models
When the criterion is the maximum R2 value, you can select to use the Huber loss function to fit TreeNet® models. The Huber function is a hybrid of the maximum R-squared and the minimum mean absolute deviation functions. With the Huber function, specify a switching value. The loss function starts as the squared error. The loss function remains the squared error as long as the value is less than the switching value. If the squared error exceeds the switching value, then the loss function becomes the absolute deviation. If the absolute deviation becomes less than the switching value, then the loss function becomes the squared error again.
Minimum mean absolute deviation
This method minimizes the sum of absolute values of errors.

Individual tree complexity parameter for TreeNet® Regression models

Choose one of the following to limit the size of the trees.
  • Maximum terminal nodes per tree: Enter a value between 2 and 2000 to represent the maximum number of terminal nodes of a tree. Usually, a value of 6 provides a good balance between calculation speed and the investigation of interactions among variables. A value of 2 eliminates the investigation of interactions.
  • Maximum tree depth: Enter a value between 2 and 1000 to represent the maximum depth of a tree. The root node corresponds to a depth of 1. In many applications, depths from 4 to 6 give reasonably good models.