public void BivariateNullAssociation()
{
Random rng = new Random(31415926);
// Create a data structure to hold the results of Pearson, Spearman, and Kendall tests.
FrameTable data = new FrameTable();
data.AddColumn <double>("r");
data.AddColumn <double>("ρ");
data.AddColumn <double>("τ");
// Create variables to hold the claimed distribution of each test statistic.
ContinuousDistribution PRD = null;
ContinuousDistribution SRD = null;
ContinuousDistribution KTD = null;
// Generate a large number of bivariate samples and conduct our three tests on each.
ContinuousDistribution xDistribution = new LognormalDistribution();
ContinuousDistribution yDistribution = new CauchyDistribution();
for (int j = 0; j < 100; j++)
{
List <double> x = new List <double>();
List <double> y = new List <double>();
for (int i = 0; i < 100; i++)
{
x.Add(xDistribution.GetRandomValue(rng));
y.Add(yDistribution.GetRandomValue(rng));
}
TestResult PR = Bivariate.PearsonRTest(x, y);
TestResult SR = Bivariate.SpearmanRhoTest(x, y);
TestResult KT = Bivariate.KendallTauTest(x, y);
PRD = PR.Statistic.Distribution;
SRD = SR.Statistic.Distribution;
KTD = KT.Statistic.Distribution;
data.AddRow(new Dictionary <string, object>()
{
{ "r", PR.Statistic.Value }, { "ρ", SR.Statistic.Value }, { "τ", KT.Statistic.Value }
});
}
Assert.IsTrue(data["r"].As <double>().KolmogorovSmirnovTest(PRD).Probability > 0.05);
Assert.IsTrue(data["ρ"].As <double>().KolmogorovSmirnovTest(SRD).Probability > 0.05);
Assert.IsTrue(data["τ"].As <double>().KolmogorovSmirnovTest(KTD).Probability > 0.05);
}
public void MultivariateLinearLogisticRegressionVariances()
{
// define model y = a + b0 * x0 + b1 * x1 + noise
double a = -3.0;
double b0 = 2.0;
double b1 = 1.0;
ContinuousDistribution x0distribution = new ExponentialDistribution();
ContinuousDistribution x1distribution = new LognormalDistribution();
FrameTable data = new FrameTable();
data.AddColumns <double>("a", "da", "b0", "db0", "b1", "db1", "p", "dp");
// draw a sample from the model
Random rng = new Random(2);
for (int j = 0; j < 32; j++)
{
List <double> x0s = new List <double>();
List <double> x1s = new List <double>();
List <bool> ys = new List <bool>();
FrameTable table = new FrameTable();
table.AddColumn <double>("x0");
table.AddColumn <double>("x1");
table.AddColumn <bool>("y");
for (int i = 0; i < 32; i++)
{
double x0 = x0distribution.GetRandomValue(rng);
double x1 = x1distribution.GetRandomValue(rng);
double t = a + b0 * x0 + b1 * x1;
double p = 1.0 / (1.0 + Math.Exp(-t));
bool y = (rng.NextDouble() < p);
x0s.Add(x0);
x1s.Add(x1);
ys.Add(y);
}
// do a linear regression fit on the model
MultiLinearLogisticRegressionResult result = ys.MultiLinearLogisticRegression(
new Dictionary <string, IReadOnlyList <double> > {
{ "x0", x0s }, { "x1", x1s }
}
);
UncertainValue pp = result.Predict(0.0, 1.0);
data.AddRow(
result.Intercept.Value, result.Intercept.Uncertainty,
result.CoefficientOf("x0").Value, result.CoefficientOf("x0").Uncertainty,
result.CoefficientOf("x1").Value, result.CoefficientOf("x1").Uncertainty,
pp.Value, pp.Uncertainty
);
}
// The estimated parameters should agree with the model that generated the data.
// The variances of the estimates should agree with the claimed variances
Assert.IsTrue(data["a"].As <double>().PopulationStandardDeviation().ConfidenceInterval(0.99).ClosedContains(data["da"].As <double>().Mean()));
Assert.IsTrue(data["b0"].As <double>().PopulationStandardDeviation().ConfidenceInterval(0.99).ClosedContains(data["db0"].As <double>().Mean()));
Assert.IsTrue(data["b1"].As <double>().PopulationStandardDeviation().ConfidenceInterval(0.99).ClosedContains(data["db1"].As <double>().Mean()));
Assert.IsTrue(data["p"].As <double>().PopulationStandardDeviation().ConfidenceInterval(0.99).ClosedContains(data["dp"].As <double>().Mean()));
}
