private double getClusterP2(List<Node> c) {
Graph g = new EdgeListGraph(c);
Node l = new GraphNode("L");
l.setNodeType(NodeType.LATENT);
g.addNode(l);
for (Node n : c) {
g.addDirectedEdge(l, n);
}
SemPm pm = new SemPm(g);
SemEstimator est;
if (dataModel instanceof DataSet) {
est = new SemEstimator((DataSet) dataModel, pm, new SemOptimizerEm());
} else {
est = new SemEstimator((CovarianceMatrix) dataModel, pm, new SemOptimizerEm());
}
SemIm estIm = est.estimate();
double pValue = estIm.getPValue();
return pValue == 1 ? Double.NaN : pValue;
}
private String reportIfContinuous(Graph dag, DataSet dataSet) {
SemPm semPm = new SemPm(dag);
SemEstimator estimator = new SemEstimator(dataSet, semPm);
estimator.estimate();
SemIm semIm = estimator.getEstimatedSem();
NumberFormat nf = NumberFormat.getInstance();
nf.setMaximumFractionDigits(4);
StringBuilder buf = new StringBuilder();
buf.append("\nDegrees of Freedom = ")
.append(semPm.getDof())
.append("Chi-Square = ")
.append(nf.format(semIm.getChiSquare()))
.append("\nP Value = ")
.append(nf.format(semIm.getPValue()))
.append("\nBIC Score = ")
.append(nf.format(semIm.getBicScore()));
buf.append(
"\n\nThe above chi square test assumes that the maximum "
+ "likelihood function over the measured variables has been "
+ "maximized. Under that assumption, the null hypothesis for "
+ "the test is that the population covariance matrix over all "
+ "of the measured variables is equal to the estimated covariance "
+ "matrix over all of the measured variables written as a function "
+ "of the free model parameters--that is, the unfixed parameters "
+ "for each directed edge (the linear coefficient for that edge), "
+ "each exogenous variable (the variance for the error term for "
+ "that variable), and each bidirected edge (the covariance for "
+ "the exogenous variables it connects). The model is explained "
+ "in Bollen, Structural Equations with Latent Variable, 110. ");
return buf.toString();
}
private String compileReport() {
StringBuilder builder = new StringBuilder();
builder.append("Datset\tFrom\tTo\tType\tValue\tSE\tT\tP");
java.util.List<SemEstimator> estimators = wrapper.getMultipleResultList();
for (int i = 0; i < estimators.size(); i++) {
SemEstimator estimator = estimators.get(i);
SemIm estSem = estimator.getEstimatedSem();
String dataName = estimator.getDataSet().getName();
for (Parameter parameter : estSem.getFreeParameters()) {
builder.append("\n");
builder.append(dataName + "\t");
builder.append(parameter.getNodeA() + "\t");
builder.append(parameter.getNodeB() + "\t");
builder.append(typeString(parameter) + "\t");
builder.append(asString(paramValue(estSem, parameter)) + "\t");
/*
Maximum number of free parameters for which statistics will be
calculated. (Calculating standard errors is high complexity.) Set this to
zero to turn off statistics calculations (which can be problematic
sometimes).
*/
int maxFreeParamsForStatistics = 200;
builder.append(
asString(estSem.getStandardError(parameter, maxFreeParamsForStatistics)) + "\t");
builder.append(asString(estSem.getTValue(parameter, maxFreeParamsForStatistics)) + "\t");
builder.append(asString(estSem.getPValue(parameter, maxFreeParamsForStatistics)) + "\t");
}
List<Node> nodes = estSem.getVariableNodes();
for (int j = 0; j < nodes.size(); j++) {
Node node = nodes.get(j);
int n = estSem.getSampleSize();
int df = n - 1;
double mean = estSem.getMean(node);
double stdDev = estSem.getMeanStdDev(node);
double stdErr = stdDev / Math.sqrt(n);
double tValue = mean / stdErr;
double p = 2.0 * (1.0 - ProbUtils.tCdf(Math.abs(tValue), df));
builder.append("\n");
builder.append(dataName + "\t");
builder.append(nodes.get(j) + "\t");
builder.append(nodes.get(j) + "\t");
builder.append("Mean" + "\t");
builder.append(asString(mean) + "\t");
builder.append(asString(stdErr) + "\t");
builder.append(asString(tValue) + "\t");
builder.append(asString(p) + "\t");
}
}
return builder.toString();
}
