private static Element makeVariables(SemIm semIm) {
Element variablesElement = new Element(SemXmlConstants.SEM_VARIABLES);
Element variable;
Node measuredNode, latentNode;
for (Node node1 : semIm.getSemPm().getMeasuredNodes()) {
measuredNode = node1;
variable = new Element(SemXmlConstants.CONTINUOUS_VARIABLE);
variable.addAttribute(new Attribute(SemXmlConstants.NAME, measuredNode.getName()));
variable.addAttribute(new Attribute(SemXmlConstants.IS_LATENT, "no"));
variable.addAttribute(
new Attribute(SemXmlConstants.MEAN, Double.toString(semIm.getMean(measuredNode))));
variable.addAttribute(
new Attribute(SemXmlConstants.X, Integer.toString(measuredNode.getCenterX())));
variable.addAttribute(
new Attribute(SemXmlConstants.Y, Integer.toString(measuredNode.getCenterY())));
variablesElement.appendChild(variable);
}
for (Node node : semIm.getSemPm().getLatentNodes()) {
latentNode = node;
variable = new Element(SemXmlConstants.CONTINUOUS_VARIABLE);
variable.addAttribute(new Attribute(SemXmlConstants.NAME, latentNode.getName()));
variable.addAttribute(new Attribute(SemXmlConstants.IS_LATENT, "yes"));
variable.addAttribute(
new Attribute(SemXmlConstants.MEAN, Double.toString(semIm.getMean(latentNode))));
variable.addAttribute(
new Attribute(SemXmlConstants.X, Integer.toString(latentNode.getCenterX())));
variable.addAttribute(
new Attribute(SemXmlConstants.Y, Integer.toString(latentNode.getCenterY())));
variablesElement.appendChild(variable);
}
return variablesElement;
}
public int getNodeIndex(Node node) {
List<Node> nodes = semIm.getSemPm().getVariableNodes();
for (int i = 0; i < nodes.size(); i++) {
Node _node = nodes.get(i);
if (node == _node) {
return i;
}
}
return -1;
}
public int getNodeIndex(String nodeName) {
List<Node> nodes = semIm.getSemPm().getVariableNodes();
for (int i = 0; i < nodes.size(); i++) {
Node node = nodes.get(i);
if (node.getName().equals(nodeName)) {
return i;
}
}
return -1;
}
private static Element makeMarginalErrorDistribution(SemIm semIm) {
Element marginalErrorElement = new Element(SemXmlConstants.MARGINAL_ERROR_DISTRIBUTION);
Element normal;
SemGraph semGraph = semIm.getSemPm().getGraph();
semGraph.setShowErrorTerms(true);
for (Node node : getExogenousNodes(semGraph)) {
normal = new Element(SemXmlConstants.NORMAL);
normal.addAttribute(new Attribute(SemXmlConstants.VARIABLE, node.getName()));
normal.addAttribute(new Attribute(SemXmlConstants.MEAN, "0.0"));
normal.addAttribute(
new Attribute(
SemXmlConstants.VARIANCE, Double.toString(semIm.getParamValue(node, node))));
marginalErrorElement.appendChild(normal);
}
return marginalErrorElement;
}
private static Element makeJointErrorDistribution(SemIm semIm) {
Element jointErrorElement = new Element(SemXmlConstants.JOINT_ERROR_DISTRIBUTION);
Element normal;
Parameter param;
for (Parameter parameter : semIm.getSemPm().getParameters()) {
param = parameter;
if (param.getType() == ParamType.COVAR) {
normal = new Element(SemXmlConstants.NORMAL);
normal.addAttribute(new Attribute(SemXmlConstants.NODE_1, param.getNodeA().getName()));
normal.addAttribute(new Attribute(SemXmlConstants.NODE_2, param.getNodeB().getName()));
normal.addAttribute(
new Attribute(SemXmlConstants.COVARIANCE, Double.toString(param.getStartingValue())));
jointErrorElement.appendChild(normal);
}
}
return jointErrorElement;
}
private static Element makeEdges(SemIm semIm) {
Element edgesElement = new Element(SemXmlConstants.EDGES);
Parameter param;
Element edge;
for (Parameter parameter : semIm.getSemPm().getParameters()) {
param = parameter;
if (param.getType() == ParamType.COEF) {
edge = new Element(SemXmlConstants.EDGE);
edge.addAttribute(new Attribute(SemXmlConstants.CAUSE_NODE, param.getNodeA().getName()));
edge.addAttribute(new Attribute(SemXmlConstants.EFFECT_NODE, param.getNodeB().getName()));
edge.addAttribute(
new Attribute(SemXmlConstants.VALUE, Double.toString(semIm.getParamValue(param))));
edge.addAttribute(
new Attribute(SemXmlConstants.FIXED, Boolean.valueOf(param.isFixed()).toString()));
edgesElement.appendChild(edge);
}
}
return edgesElement;
}
protected SemIm estimateCoeffs(SemIm semIm) {
// System.out.print("\n****************\nCalling 2SLS... ");
SemGraph semGraph = semIm.getSemPm().getGraph();
// Get list of fixed measurements that will be kept fixed, and the
// respective latent variables that are their parents.
// "X" variables are exogenous, while "Y" variables are endogenous.
List<Node> ly = new LinkedList<Node>();
List<Node> lx = new LinkedList<Node>();
List<Node> my1 = new LinkedList<Node>();
List<Node> mx1 = new LinkedList<Node>();
List<Node> observed = new LinkedList<Node>();
for (Node nodeA : semGraph.getNodes()) {
if (nodeA.getNodeType() == NodeType.ERROR) {
continue;
}
if (nodeA.getNodeType() == NodeType.LATENT) {
if (semGraph.getParents(nodeA).size() == 0) {
lx.add(nodeA);
} else {
ly.add(nodeA);
}
} else {
observed.add(nodeA);
}
}
setFixedNodes(semGraph, mx1, my1);
// ------------------------------------------------------------------
// Estimate freeParameters for the latent/latent edges
for (Node current : ly) {
if (nodeName != null && !nodeName.equals(current.getName())) {
continue;
}
// Build Z, the matrix containing the data for the fixed measurements
// associated with the parents of the getModel (endogenous) latent node
List<Node> endo_parents_m = new LinkedList<Node>();
List<Node> exo_parents_m = new LinkedList<Node>();
List<Node> endo_parents = new LinkedList<Node>();
List<Node> exo_parents = new LinkedList<Node>();
Iterator<Node> it_p = semGraph.getParents(current).iterator();
lNames = new String[lx.size() + ly.size()];
while (it_p.hasNext()) {
Node node = it_p.next();
if (node.getNodeType() == NodeType.ERROR) {
continue;
}
if (lx.contains(node)) {
int position = lx.indexOf(node);
exo_parents_m.add(mx1.get(position));
exo_parents.add(node);
} else {
int position = ly.indexOf(node);
endo_parents_m.add(my1.get(position));
endo_parents.add(node);
}
}
Object endp_a_m[] = endo_parents_m.toArray();
Object exop_a_m[] = exo_parents_m.toArray();
Object endp_a[] = endo_parents.toArray();
Object exop_a[] = exo_parents.toArray();
int n = dataSet.getNumRows(), c = endp_a_m.length + exop_a_m.length;
if (c == 0) {
continue;
}
double Z[][] = new double[n][c];
int count = 0;
for (int i = 0; i < endp_a_m.length; i++) {
Node node = (Node) endp_a_m[i];
String name = node.getName();
Node variable = dataSet.getVariable(name);
int colIndex = dataSet.getVariables().indexOf(variable);
// Column column = dataSet.getColumnObject(variable);
// double column_data[] = (double[]) column.getRawData();
for (int j = 0; j < n; j++) {
// Z[j][i] = column_data[j];
Z[j][i] = dataSet.getDouble(j, colIndex);
}
lNames[count++] = (endo_parents.get(i)).getName();
}
for (int i = 0; i < exop_a_m.length; i++) {
Node node = (Node) exop_a_m[i];
String name = node.getName();
Node variable = dataSet.getVariable(name);
int colIndex = dataSet.getVariables().indexOf(variable);
// Column column = dataSet.getColumnObject(variable);
// double column_data[] = (double[]) column.getRawData();
for (int j = 0; j < n; j++) {
// Z[j][endp_a_m.length + i] = column_data[j];
Z[j][endp_a_m.length + i] = dataSet.getDouble(j, colIndex);
}
lNames[count++] = exo_parents.get(i).getName();
}
// Build V, the matrix containing the data for the nonfixed measurements
// associated with the parents of the getModel (endogenous) latent node
endo_parents_m = new LinkedList<Node>();
exo_parents_m = new LinkedList<Node>();
it_p = semGraph.getParents(current).iterator();
while (it_p.hasNext()) {
Node node = it_p.next();
if (node.getNodeType() == NodeType.ERROR) {
continue;
}
List<Node> other_measures = new LinkedList<Node>();
for (Node next : semGraph.getChildren(node)) {
if (next.getNodeType() == NodeType.MEASURED) {
other_measures.add(next);
}
}
if (lx.contains(node)) {
int position = lx.indexOf(node);
other_measures.remove(mx1.get(position));
exo_parents_m.addAll(other_measures);
} else {
int position = ly.indexOf(node);
other_measures.remove(my1.get(position));
endo_parents_m.addAll(other_measures);
}
}
endp_a_m = endo_parents_m.toArray();
exop_a_m = exo_parents_m.toArray();
n = dataSet.getNumRows();
c = endp_a_m.length + exop_a_m.length;
double V[][] = new double[n][c];
if (c == 0) {
continue;
}
for (int i = 0; i < endp_a_m.length; i++) {
Node node = ((Node) endp_a_m[i]);
String name = node.getName();
Node variable = dataSet.getVariable(name);
int colIndex = dataSet.getVariables().indexOf(variable);
// Column column = dataSet.getColumnObject(variable);
// double column_data[] = (double[]) column.getRawData();
for (int j = 0; j < n; j++) {
// V[j][i] = column_data[j];
V[j][i] = dataSet.getDouble(j, colIndex);
}
}
for (int i = 0; i < exop_a_m.length; i++) {
Node node = (Node) exop_a_m[i];
String name = node.getName();
Node variable = dataSet.getVariable(name);
int colIndex = dataSet.getVariables().indexOf(variable);
// Column column = dataSet.getColumnObject(variable);
// double column_data[] = (double[]) column.getRawData();
for (int j = 0; j < n; j++) {
// V[j][endp_a_m.length + i] = column_data[j];
V[j][endp_a_m.length + i] = dataSet.getDouble(j, colIndex);
}
}
double yi[] = new double[n];
if (lx.contains(current)) {
int position = lx.indexOf(current);
Node node = mx1.get(position);
String name = node.getName();
Node variable = dataSet.getVariable(name);
int colIndex = dataSet.getVariables().indexOf(variable);
// Column column = dataSet.getColumnObject(variable);
//
// System.arraycopy(column.getRawData(), 0, yi, 0, n);
for (int i = 0; i < n; i++) {
yi[i] = dataSet.getDouble(i, colIndex);
}
} else {
int position = ly.indexOf(current);
Node node = my1.get(position);
String name = node.getName();
Node variable = dataSet.getVariable(name);
int colIndex = dataSet.getVariables().indexOf(variable);
// System.arraycopy(dataSet.getColumnObject(variable).getRawData(), 0, yi, 0,
// n);
for (int i = 0; i < n; i++) {
yi[i] = dataSet.getDouble(i, colIndex);
}
}
// Build Z_hat
double Z_hat[][] =
MatrixUtils.product(
V,
MatrixUtils.product(
MatrixUtils.inverse(MatrixUtils.product(MatrixUtils.transpose(V), V)),
MatrixUtils.product(MatrixUtils.transpose(V), Z)));
A_hat =
MatrixUtils.product(
MatrixUtils.inverse(MatrixUtils.product(MatrixUtils.transpose(Z_hat), Z_hat)),
MatrixUtils.product(MatrixUtils.transpose(Z_hat), yi));
// Set the edge for the fixed measurement
int position = ly.indexOf(current);
semIm.setParamValue(current, my1.get(position), 1.);
// Set the edge for the latents
for (int i = 0; i < endp_a.length; i++) {
semIm.setParamValue((Node) endp_a[i], current, A_hat[i]);
}
for (int i = 0; i < exop_a.length; i++) {
semIm.setParamValue((Node) exop_a[i], current, A_hat[endp_a.length + i]);
}
if (nodeName != null && nodeName.equals(current.getName())) {
computeAsymptLatentCovar(yi, A_hat, Z, Z_hat, dataSet.getNumRows());
break;
}
}
// ------------------------------------------------------------------
// Estimate freeParameters of the measurement model
// Set the edges of the fixed measurements of exogenous
for (Node current : lx) {
int position = lx.indexOf(current);
semIm.setParamValue(current, mx1.get(position), 1.);
}
for (Node current : observed) {
if (nodeName != null && !nodeName.equals(current.getName())) {
continue;
}
if (mx1.contains(current) || my1.contains(current)) {
continue;
}
// First, get the parent of this observed
Node current_latent = null;
for (Node node : semGraph.getParents(current)) {
if (node.getNodeType() == NodeType.ERROR) {
continue;
}
current_latent = node;
}
Iterator<Node> children = semGraph.getChildren(current_latent).iterator();
List<Node> other_measures = new LinkedList<Node>();
Node fixed_measurement;
while (children.hasNext()) {
Node next = children.next();
if ((next.getNodeType() == NodeType.MEASURED) && next != current) {
other_measures.add(next);
}
}
if (lx.contains(current_latent)) {
int position = lx.indexOf(current_latent);
other_measures.remove(mx1.get(position));
fixed_measurement = mx1.get(position);
} else {
int position = ly.indexOf(current_latent);
other_measures.remove(my1.get(position));
fixed_measurement = my1.get(position);
}
// Regress other_measures over the fixed measurement x1 (y1) correspondent
// to the measurement variable that is being evaluated
int n = dataSet.getNumRows(), c = other_measures.size();
if (c == 0) {
continue;
}
double Z[][] = new double[n][c];
for (int i = 0; i < c; i++) {
Node variable = dataSet.getVariable((other_measures.get(i)).getName());
int varIndex = dataSet.getVariables().indexOf(variable);
// Column column = dataSet.getColumnObject(variable);
// double column_data[] = (double[]) column.getRawData();
for (int j = 0; j < n; j++) {
// Z[j][i] = column_data[j];
Z[j][i] = dataSet.getDouble(varIndex, j);
}
}
// Build C, the column matrix containing the data for the fixed
// measurement associated with the only latent parent of the getModel
// observed node (as assumed by the structure of our measurement model).
Node variable = dataSet.getVariable(fixed_measurement.getName());
int colIndex = dataSet.getVariables().indexOf(variable);
// Column column = dataSet.getColumnObject(variable);
// double C[] = (double[]) column.getRawData();
double[] C = new double[dataSet.getNumRows()];
for (int i = 0; i < dataSet.getNumRows(); i++) {
C[i] = dataSet.getDouble(colIndex, i);
}
// Build V, the matrix containing the data for the other measurements
// associated with the parents of the (latent) parent of getModel
// observed node. The only difference with respect to the estimation
// of the within-latent coefficients is that here we only include
// the other measurements attached to the parent of the getModel node,
// assuming that the error term of the getModel node is independent
// of the error term of the others and that each measurement is
// taken with respect to only one latent.
n = dataSet.getNumRows();
c = other_measures.size();
double V[][] = new double[n][c];
for (int i = 0; i < c; i++) {
Node variable2 = dataSet.getVariable((other_measures.get(i)).getName());
int var2index = dataSet.getVariables().indexOf(variable2);
// Column column = dataSet.getColumnObject(variable2);
// double column_data[] = (double[]) column.getRawData();
for (int j = 0; j < n; j++) {
// V[j][i] = column_data[j];
V[j][i] = dataSet.getDouble(j, var2index);
}
}
double yi[] = new double[n];
Node variable3 = dataSet.getVariable((current).getName());
int var3Index = dataSet.getVariables().indexOf(variable3);
for (int i = 0; i < n; i++) {
yi[i] = dataSet.getDouble(i, var3Index);
}
// Object rawData = dataSet.getColumnObject(variable3).getRawData();
// System.arraycopy(rawData, 0, yi, 0, n);
double C_hat[] =
MatrixUtils.product(
V,
MatrixUtils.product(
MatrixUtils.inverse(MatrixUtils.product(MatrixUtils.transpose(V), V)),
MatrixUtils.product(MatrixUtils.transpose(V), C)));
double A_hat =
MatrixUtils.innerProduct(
MatrixUtils.scalarProduct(1. / MatrixUtils.innerProduct(C_hat, C_hat), C_hat), yi);
// Set the edge for the getModel measurement
semIm.setParamValue(current_latent, current, A_hat);
}
return semIm;
}
/**
* Constructs a new standardized SEM IM from the freeParameters in the given SEM IM.
*
* @param im Stop asking me for these things! The given SEM IM!!!
* @param initialization CALCULATE_FROM_SEM if the initial values will be calculated from the
* given SEM IM; INITIALIZE_FROM_DATA if data will be simulated from the given SEM,
* standardized, and estimated.
*/
public StandardizedSemIm(SemIm im, Initialization initialization) {
this.semPm = new SemPm(im.getSemPm());
this.semGraph = new SemGraph(semPm.getGraph());
semGraph.setShowErrorTerms(true);
if (semGraph.existsDirectedCycle()) {
throw new IllegalArgumentException("The cyclic case is not handled.");
}
if (initialization == Initialization.CALCULATE_FROM_SEM) {
// This code calculates the new coefficients directly from the old ones.
edgeParameters = new HashMap<Edge, Double>();
List<Node> nodes = im.getVariableNodes();
TetradMatrix impliedCovar = im.getImplCovar(true);
for (Parameter parameter : im.getSemPm().getParameters()) {
if (parameter.getType() == ParamType.COEF) {
Node a = parameter.getNodeA();
Node b = parameter.getNodeB();
int aindex = nodes.indexOf(a);
int bindex = nodes.indexOf(b);
double vara = impliedCovar.get(aindex, aindex);
double stda = Math.sqrt(vara);
double varb = impliedCovar.get(bindex, bindex);
double stdb = Math.sqrt(varb);
double oldCoef = im.getEdgeCoef(a, b);
double newCoef = (stda / stdb) * oldCoef;
edgeParameters.put(Edges.directedEdge(a, b), newCoef);
} else if (parameter.getType() == ParamType.COVAR) {
Node a = parameter.getNodeA();
Node b = parameter.getNodeB();
Node exoa = semGraph.getExogenous(a);
Node exob = semGraph.getExogenous(b);
double covar = im.getErrCovar(a, b) / Math.sqrt(im.getErrVar(a) * im.getErrVar(b));
edgeParameters.put(Edges.bidirectedEdge(exoa, exob), covar);
}
}
} else {
// This code estimates the new coefficients from simulated data from the old model.
DataSet dataSet = im.simulateData(1000, false);
TetradMatrix _dataSet = dataSet.getDoubleData();
_dataSet = DataUtils.standardizeData(_dataSet);
DataSet dataSetStandardized = ColtDataSet.makeData(dataSet.getVariables(), _dataSet);
SemEstimator estimator = new SemEstimator(dataSetStandardized, im.getSemPm());
SemIm imStandardized = estimator.estimate();
edgeParameters = new HashMap<Edge, Double>();
for (Parameter parameter : imStandardized.getSemPm().getParameters()) {
if (parameter.getType() == ParamType.COEF) {
Node a = parameter.getNodeA();
Node b = parameter.getNodeB();
double coef = imStandardized.getEdgeCoef(a, b);
edgeParameters.put(Edges.directedEdge(a, b), coef);
} else if (parameter.getType() == ParamType.COVAR) {
Node a = parameter.getNodeA();
Node b = parameter.getNodeB();
Node exoa = semGraph.getExogenous(a);
Node exob = semGraph.getExogenous(b);
double covar = -im.getErrCovar(a, b) / Math.sqrt(im.getErrVar(a) * im.getErrVar(b));
edgeParameters.put(Edges.bidirectedEdge(exoa, exob), covar);
}
}
}
this.measuredNodes = Collections.unmodifiableList(semPm.getMeasuredNodes());
}
