Package edu.cmu.tetrad.search
Class Ida
java.lang.Object
edu.cmu.tetrad.search.Ida
Implements the IDA algorithm. The reference is here:
Maathuis, Marloes H., Markus Kalisch, and Peter Bühlmann. "Estimating high-dimensional intervention effects from observational data." The Annals of Statistics 37.6A (2009): 3133-3164.
The IDA algorithm seeks to give a list of possible parents of a given variable Y and their corresponding lower-bounded effects on Y.
- Version:
- $Id: $Id
- Author:
- josephramsey
- See Also:
-
Nested Class Summary
Nested ClassesModifier and TypeClassDescriptionstatic class
Gives a list of nodes (parents or children) and corresponding minimum effects for the IDA algorithm. -
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionReturns a map from nodes in V \ {Y} to their minimum effects.double
distance
(LinkedList<Double> effects, double trueEffect) Returns the distance between the effects and the true effect.Returns the minimum effects of X on Y for X in V \ {Y}, sorted downward by minimum effectdouble
trueEffect
(Node x, Node y, Graph trueDag) Calculates the true effect of node x on node y in a given graph.
-
Constructor Details
-
Ida
Constructor.- Parameters:
dataSet
- The dataset being searched over.cpdag
- The CPDAG (found, e.g., by running PC, or some other CPDAG producing algorithm.possibleCauses
- The possible causes to be considered.
-
-
Method Details
-
getSortedMinEffects
Returns the minimum effects of X on Y for X in V \ {Y}, sorted downward by minimum effect- Parameters:
y
- The child variable.- Returns:
- Two sorted lists, one of possible parents, the other of corresponding minimum effects, sorted downward by minimum effect size.
- See Also:
-
trueEffect
Calculates the true effect of node x on node y in a given graph.- Parameters:
x
- The first node.y
- The second node.trueDag
- The graph representing the true underlying causal structure.- Returns:
- The true effect of x on y.
- Throws:
IllegalArgumentException
- If x is equal to y.
-
distance
Returns the distance between the effects and the true effect.- Parameters:
effects
- aLinkedList
objecttrueEffect
- a double- Returns:
- This difference.
-
calculateMinimumEffectsOnY
Returns a map from nodes in V \ {Y} to their minimum effects.- Parameters:
y
- The child variable- Returns:
- Thia map.
-