Package edu.cmu.tetrad.sem

Class LargeScaleSimulation

java.lang.Object

edu.cmu.tetrad.sem.LargeScaleSimulation

public final class LargeScaleSimulation
extends Object

Stores a SEM model, pared down, for purposes of simulating data sets with large numbers of variables and sample sizes.

Version:

$Id: $Id

Author:

josephramsey

Constructor Summary

Constructors

Constructor	Description
LargeScaleSimulation(Graph graph)	Constructor for LargeScaleSimulation.
LargeScaleSimulation(Graph graph, List<Node> nodes, int[] tierIndices)	Constructor for LargeScaleSimulation.

Method Summary

Modifier and Type	Method	Description
double[][]	getCoefficientMatrix()	getCoefficientMatrix.
Graph	getGraph()	Getter for the field graph.
static int	getIndex(String s)	getIndex.
Knowledge	getKnowledge(Graph graph)	getKnowledge.
static int	getLag(String s)	getLag.
String	getNameNoLag(Object obj)	getNameNoLag.
PrintStream	getOut()	Getter for the field out.
static String	getPrefix(String s)	getPrefix.
double	getSelfLoopCoef()	Getter for the field selfLoopCoef.
double[][]	getSoCalledPoissonShocks(int sampleSize)	getSoCalledPoissonShocks.
double[][]	getUncorrelatedShocks(int sampleSize)	getUncorrelatedShocks.
List<Node>	getVariableNodes()	Getter for the field variableNodes.
boolean	isVerbose()	isVerbose.
void	setCoefRange(double coefLow, double coefHigh)	setCoefRange.
void	setErrorsNormal(boolean errorsNormal)	Setter for the field errorsNormal.
void	setIncludeNegativeCoefs(boolean includeNegativeCoefs)	Setter for the field includeNegativeCoefs.
void	setIncludePositiveCoefs(boolean includePositiveCoefs)	Setter for the field includePositiveCoefs.
void	setMeanRange(double meanLow, double meanHigh)	setMeanRange.
void	setOut(PrintStream out)	Setter for the field out.
void	setSelfLoopCoef(double selfLoopCoef)	Setter for the field selfLoopCoef.
void	setVarRange(double varLow, double varHigh)	setVarRange.
void	setVerbose(boolean verbose)	Setter for the field verbose.
DataSet	simulateDataFisher(double[][] shocks, int intervalBetweenShocks, double epsilon)	Simulates data using the model of R.
DataSet	simulateDataFisher(int sampleSize)	Simulates data using the model of R.
DataSet	simulateDataFisher(int intervalBetweenShocks, int intervalBetweenRecordings, int sampleSize, double epsilon, boolean saveLatentVars)	simulateDataFisher.
DataSet	simulateDataRecursive(int sampleSize)	This simulates data by picking random values for the exogenous terms and percolating this information down through the SEM, assuming it is acyclic.
DataSet	simulateDataReducedForm(int sampleSize)	Simulates data using the model X = (I - B)Y^-1 * e.

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

LargeScaleSimulation

public LargeScaleSimulation(Graph graph)

Constructor for LargeScaleSimulation.

Parameters:

graph - a Graph object

LargeScaleSimulation

public LargeScaleSimulation(Graph graph,
 List<Node> nodes,
 int[] tierIndices)

Constructor for LargeScaleSimulation.

Parameters:

graph - a Graph object

nodes - a List object

tierIndices - an array of objects

Method Details

getPrefix

public static String getPrefix(String s)

getPrefix.

Parameters:

s - a String object

Returns:

a String object

getIndex

public static int getIndex(String s)

getIndex.

Parameters:

s - a String object

Returns:

a int

getLag

public static int getLag(String s)

getLag.

Parameters:

s - a String object

Returns:

a int

simulateDataRecursive

public DataSet simulateDataRecursive(int sampleSize)

This simulates data by picking random values for the exogenous terms and percolating this information down through the SEM, assuming it is acyclic. Works, but will hang for cyclic models, and is very slow for large numbers of variables (probably due to the heavyweight lookups of various values--could be improved). The model must be acyclic, or else this will spin.

Parameters:

sampleSize - a int

Returns:

a DataSet object

simulateDataReducedForm

public DataSet simulateDataReducedForm(int sampleSize)

Simulates data using the model X = (I - B)Y^-1 * e. Errors are uncorrelated.

Parameters:

sampleSize - The nubmer of samples to draw.

Returns:

a DataSet object

simulateDataFisher

public DataSet simulateDataFisher(int sampleSize)

Simulates data using the model of R. A. Fisher, for a linear model. Shocks are applied every so many steps. A data point is recorded before each shock is administered. If convergence happens before that number of steps has been reached, a data point is recorded and a new shock immediately applied. The model may be cyclic. If cyclic, all eigenvalues for the coefficient matrix must be less than 1, though this is not checked. Uses an interval between shocks of 50 and a convergence threshold of 1e-5. Uncorrelated Gaussian shocks are used.

Parameters:

sampleSize - The number of samples to be drawn. Must be a positive integer.

Returns:

a DataSet object

simulateDataFisher

public DataSet simulateDataFisher(double[][] shocks,
 int intervalBetweenShocks,
 double epsilon)

Simulates data using the model of R. A. Fisher, for a linear model. Shocks are applied every so many steps. A data point is recorded before each shock is administered. If convergence happens before that number of steps has been reached, a data point is recorded and a new shock immediately applied. The model may be cyclic. If cyclic, all eigenvalues for the coefficient matrix must be less than 1, though this is not checked.

Parameters:

shocks - A matrix of shocks. The value at shocks[i][j] is the shock for the i'th time step, for the j'th variables.

intervalBetweenShocks - External shock is applied every this many steps. Must be positive integer.

epsilon - The convergence criterion; |xi.t - xi.t-1| < epsilon.fff

Returns:

a DataSet object

simulateDataFisher

public DataSet simulateDataFisher(int intervalBetweenShocks,
 int intervalBetweenRecordings,
 int sampleSize,
 double epsilon,
 boolean saveLatentVars)

simulateDataFisher.

Parameters:

intervalBetweenShocks - a int

intervalBetweenRecordings - a int

sampleSize - a int

epsilon - a double

saveLatentVars - a boolean

Returns:

a DataSet object

getGraph

public Graph getGraph()

Getter for the field graph.

Returns:

a Graph object

setCoefRange

public void setCoefRange(double coefLow,
 double coefHigh)

setCoefRange.

Parameters:

coefLow - a double

coefHigh - a double

setVarRange

public void setVarRange(double varLow,
 double varHigh)

setVarRange.

Parameters:

varLow - a double

varHigh - a double

setMeanRange

public void setMeanRange(double meanLow,
 double meanHigh)

setMeanRange.

Parameters:

meanLow - a double

meanHigh - a double

getOut

public PrintStream getOut()

Getter for the field out.

Returns:

a PrintStream object

setOut

public void setOut(PrintStream out)

Setter for the field out.

Parameters:

out - a PrintStream object

isVerbose

public boolean isVerbose()

isVerbose.

Returns:

a boolean

setVerbose

public void setVerbose(boolean verbose)

Setter for the field verbose.

Parameters:

verbose - a boolean

getCoefficientMatrix

public double[][] getCoefficientMatrix()

getCoefficientMatrix.

Returns:

an array of objects

getVariableNodes

public List<Node> getVariableNodes()

Getter for the field variableNodes.

Returns:

a List object

getNameNoLag

public String getNameNoLag(Object obj)

getNameNoLag.

Parameters:

obj - a Object object

Returns:

a String object

getKnowledge

public Knowledge getKnowledge(Graph graph)

getKnowledge.

Parameters:

graph - a Graph object

Returns:

a Knowledge object

getUncorrelatedShocks

public double[][] getUncorrelatedShocks(int sampleSize)

getUncorrelatedShocks.

Parameters:

sampleSize - a int

Returns:

an array of objects

getSoCalledPoissonShocks

public double[][] getSoCalledPoissonShocks(int sampleSize)

getSoCalledPoissonShocks.

Parameters:

sampleSize - a int

Returns:

an array of objects

setIncludePositiveCoefs

public void setIncludePositiveCoefs(boolean includePositiveCoefs)

Setter for the field includePositiveCoefs.

Parameters:

includePositiveCoefs - a boolean

setIncludeNegativeCoefs

public void setIncludeNegativeCoefs(boolean includeNegativeCoefs)

Setter for the field includeNegativeCoefs.

Parameters:

includeNegativeCoefs - a boolean

setErrorsNormal

public void setErrorsNormal(boolean errorsNormal)

Setter for the field errorsNormal.

Parameters:

errorsNormal - a boolean

getSelfLoopCoef

public double getSelfLoopCoef()

Getter for the field selfLoopCoef.

Returns:

a double

setSelfLoopCoef

public void setSelfLoopCoef(double selfLoopCoef)

Setter for the field selfLoopCoef.

Parameters:

selfLoopCoef - a double