private String reportIfDiscrete(Graph dag, DataSet dataSet) {
List vars = dataSet.getVariables();
Map<String, DiscreteVariable> nodesToVars = new HashMap<String, DiscreteVariable>();
for (int i = 0; i < dataSet.getNumColumns(); i++) {
DiscreteVariable var = (DiscreteVariable) vars.get(i);
String name = var.getName();
Node node = new GraphNode(name);
nodesToVars.put(node.getName(), var);
}
BayesPm bayesPm = new BayesPm(new Dag(dag));
List<Node> nodes = bayesPm.getDag().getNodes();
for (Node node : nodes) {
Node var = nodesToVars.get(node.getName());
if (var instanceof DiscreteVariable) {
DiscreteVariable var2 = nodesToVars.get(node.getName());
int numCategories = var2.getNumCategories();
List<String> categories = new ArrayList<String>();
for (int j = 0; j < numCategories; j++) {
categories.add(var2.getCategory(j));
}
bayesPm.setCategories(node, categories);
}
}
BayesProperties properties = new BayesProperties(dataSet, dag);
properties.setGraph(dag);
NumberFormat nf = NumberFormat.getInstance();
nf.setMaximumFractionDigits(4);
StringBuilder buf = new StringBuilder();
buf.append("\nP-value = ").append(properties.getLikelihoodRatioP());
buf.append("\nDf = ").append(properties.getPValueDf());
buf.append("\nChi square = ").append(nf.format(properties.getPValueChisq()));
buf.append("\nBIC score = ").append(nf.format(properties.getBic()));
buf.append("\n\nH0: Completely disconnected graph.");
return buf.toString();
}
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();
}