Class ConditionalInferenceTreeNode<T>

Namespace

AiDotNet.LinearAlgebra

Assembly

AiDotNet.dll

Represents a node in a conditional inference tree, which is a type of decision tree that uses statistical tests to make decisions at each node.

public class ConditionalInferenceTreeNode<T> : DecisionTreeNode<T>

Type Parameters

T

The numeric data type used for calculations (e.g., float, double).

Inheritance

object

DecisionTreeNode<T>

ConditionalInferenceTreeNode<T>

Inherited Members

DecisionTreeNode<T>.FeatureIndex

DecisionTreeNode<T>.Threshold

DecisionTreeNode<T>.SplitValue

DecisionTreeNode<T>.Prediction

DecisionTreeNode<T>.Left

DecisionTreeNode<T>.Right

DecisionTreeNode<T>.IsLeaf

DecisionTreeNode<T>.Samples

DecisionTreeNode<T>.LeftSampleCount

DecisionTreeNode<T>.RightSampleCount

DecisionTreeNode<T>.SampleValues

DecisionTreeNode<T>.LinearModel

DecisionTreeNode<T>.Predictions

DecisionTreeNode<T>.SumSquaredError

DecisionTreeNode<T>.UpdateNodeStatistics()

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Remarks

A conditional inference tree is a statistical approach to decision tree learning that uses significance tests to select variables at each split.

For Beginners: Think of this as a special type of decision tree that makes decisions based on statistical evidence rather than just information gain. The p-value stored in each node represents how confident we are that the split at this node is meaningful and not just due to random chance. Lower p-values (closer to zero) indicate stronger evidence for the split.

Constructors

ConditionalInferenceTreeNode()

Initializes a new instance of the ConditionalInferenceTreeNode<T> class with a default p-value of zero.

public ConditionalInferenceTreeNode()

Remarks

For Beginners: This creates a new node for the decision tree with an initial p-value of zero, which would indicate a highly significant split. As the tree is built, this value may be updated based on statistical tests.

Properties

PValue

Gets or sets the p-value associated with the statistical test at this node.

public T PValue { get; set; }

Property Value

T

Remarks

In statistical hypothesis testing, the p-value represents the probability of observing results at least as extreme as the current results, assuming the null hypothesis is true.

For Beginners: The p-value is a number between 0 and 1 that helps determine if the split at this node is statistically significant. A smaller p-value (typically below 0.05) suggests that the split is meaningful and not just due to random chance in the data.