new public double[] computeNew(object category)
{
int lblIndex = Labels.IndexOf(category.ToString());
int gN = cateDic[category.ToString()];
Accord.Statistics.Distributions.Univariate.TDistribution tDist = new Accord.Statistics.Distributions.Univariate.TDistribution(gN - 1);
double[] s = sumX[lblIndex];
double[] s2 = sumX2[lblIndex];
double[] mns = (from double d in s select d / gN).ToArray();
double[] ses = getSe(s, s2, gN);
double[] outArr = new double[mns.Length];
for (int i = 0; i < outArr.Length; i++)
{
double tStat = mns[i] / ses[i];
double cdf = tDist.DistributionFunction(tStat);
double pValue = 0;
if (tStat > 0)
{
pValue = (1 - cdf) * 2;
}
else
{
pValue = (cdf * 2);
}
outArr[i] = pValue;
}
return(outArr);
}
public static void PairedTTestPValues(double[] popMeans, double[,] popVarCov, double[] sampMeans, double[,] sampVarCov, out double meanPvalue, out double varPvalue)
{
double n = popMeans.Length;
meanPvalue = 0;
varPvalue = 0;
double sumM = 0;
double sumV = 0;
double sumM2 = 0;
double sumV2 = 0;
for (int i = 0; i < n; i++)
{
double m1 = popMeans[i];
double m2 = sampMeans[i];
double dm = m1 - m2;
double v1 = popVarCov[i, i];
double v2 = sampVarCov[i, i];
double dv = v1 - v2;
sumM += dm;
sumV += dv;
sumM2 += dm * dm;
sumV2 += dv * dv;
}
double mM = sumM / n;
double mV = sumV / n;
double seM = Math.Sqrt((sumM2 - ((sumM * sumM) / n)) / n) / Math.Sqrt(n);
double seV = Math.Sqrt((sumV2 - ((sumV * sumV) / n)) / n) / Math.Sqrt(n);
double mTstat = mM / seM;
double vTstat = mV / seV;
Accord.Statistics.Distributions.Univariate.TDistribution tDist = new Accord.Statistics.Distributions.Univariate.TDistribution(n - 1);
double mCdf = tDist.DistributionFunction(mTstat);
double vCdf = tDist.DistributionFunction(vTstat);
if (mTstat > 0)
{
meanPvalue = (1 - mCdf) * 2;
}
else
{
meanPvalue = mCdf * 2;
}
if (vTstat > 0)
{
varPvalue = (1 - vCdf) * 2;
}
else
{
varPvalue = vCdf * 2;
}
}
public double[] computeNew(object category)
{
string cat = category.ToString();
int catIndex = lbl.IndexOf(cat);
int np = ((VariableFieldNames.Length * VariableFieldNames.Length) - VariableFieldNames.Length) / 2;
double[] pValues = new double[np];
if (catIndex == -1)
{
return(pValues);
}
KMeansClusterCollection gCol = kmeans.Clusters;
KMeansCluster gClust = gCol[catIndex];
double[] mns = gClust.Mean;
double[] var = new double[mns.Length];
double nSample = gClust.Proportion * N;
double seAdjust = Math.Sqrt(2 * 1 / nSample);
for (int j = 0; j < mns.Length; j++)
{
var[j] = gClust.Covariance[j, j];
}
int cnt = 1;
int pCnt = 0;
for (int j = 0; j < mns.Length - 1; j++)
{
for (int k = cnt; k < mns.Length; k++)
{
double mD = mns[j] - mns[k];
double pSD = Math.Sqrt((var[j] + var[k]) / 2);
double se = pSD * seAdjust;
double tStat = mD / se;
Accord.Statistics.Distributions.Univariate.TDistribution tDist = new Accord.Statistics.Distributions.Univariate.TDistribution(2 * nSample - 2);
double cdf = tDist.DistributionFunction(tStat);
double pValue = 0;
if (tStat > 0)
{
pValue = (1 - cdf) * 2;
}
else
{
pValue = (cdf * 2);
}
pValues[pCnt] = pValue;
pCnt++;
}
cnt += 1;
}
return(pValues);
}
public new void getReport()
{
if (cateDic.Count<1) buildModel();
rd = new Forms.RunningProcess.frmRunningProcessDialog(false);
rd.Text = "Paired T-Test Results";
rd.TopLevel = true;
rd.pgbProcess.Visible = false;
rd.FormBorderStyle = System.Windows.Forms.FormBorderStyle.Sizable;
rd.addMessage("Input path = " + InPath);
rd.addMessage("Total Sample size = " + n.ToString());
rd.addMessage("\nLabel |Compare V1-V2 |N |Dif |T-Stat |P-Value ");
rd.addMessage("-".PadRight(83, '-'));
for (int i = 0; i < lbl.Count; i++)
{
string labelVl = Labels[i];
string l = getValue(labelVl, 8);
int gN = cateDic[labelVl];
if (gN == 1) continue;
double[] s = sumX[i];
double[] s2 = sumX2[i];
double[] mns = (from double d in s select d/gN).ToArray();
//Console.WriteLine("Means = " + mns.Length.ToString());
double[] ses = getSe(s, s2, gN);
//Console.WriteLine("Se = " + ses.Length.ToString());
double nSample = gN;
int cnt = 1;
int sCnt = 0;
for (int j = 0; j < VariableFieldNames.Length-1; j++)
{
for (int k = cnt; k < VariableFieldNames.Length; k++)
{
string fN1 = getValue(VariableFieldNames[j], 12);
string fN2 = getValue(VariableFieldNames[k], 12);
double mD = mns[sCnt];
double se = ses[sCnt];
double tStat = mD / se;
//Console.WriteLine(tStat.ToString());
Accord.Statistics.Distributions.Univariate.TDistribution tDist = new Accord.Statistics.Distributions.Univariate.TDistribution(nSample - 1);
double cdf = tDist.DistributionFunction(tStat);
double pValue = 0;
if (tStat > 0)
{
pValue = (1 - cdf) * 2;
}
else
{
pValue = (cdf * 2);
}
string pValueS = pValue.ToString();
if (pValue < 0.0001) pValueS = pValueS = "p < 0.0001";
string ln = l + "|" + fN1 + "-" + fN2 + "| " + getValue(nSample.ToString(), 6) + " | " + getValue(mD.ToString(), 6) + " | " + getValue(tStat.ToString(), 6) + " | " + getValue(pValueS,10);
rd.addMessage(ln);
sCnt += 1;
}
cnt += 1;
}
}
rd.addMessage("-".PadRight(83, '-'));
rd.enableClose();
rd.Show();
}
public new double[] computeNew(object category)
{
int lblIndex = Labels.IndexOf(category.ToString());
int gN = cateDic[category.ToString()];
Accord.Statistics.Distributions.Univariate.TDistribution tDist = new Accord.Statistics.Distributions.Univariate.TDistribution(gN - 1);
double[] s = sumX[lblIndex];
double[] s2 = sumX2[lblIndex];
double[] mns = (from double d in s select d / gN).ToArray();
double[] ses = getSe(s, s2, gN);
double[] outArr = new double[mns.Length];
for (int i = 0; i < outArr.Length; i++)
{
double tStat = mns[i] / ses[i];
double cdf = tDist.DistributionFunction(tStat);
double pValue = 0;
if (tStat > 0)
{
pValue = (1 - cdf) * 2;
}
else
{
pValue = (cdf * 2);
}
outArr[i] = pValue;
}
return outArr;
}
public void getReport()
{
if (kmeans == null) buildModel();
rd = new Forms.RunningProcess.frmRunningProcessDialog(false);
rd.Text = "Independent T-Test Results";
rd.TopLevel = true;
rd.pgbProcess.Visible = false;
rd.FormBorderStyle = System.Windows.Forms.FormBorderStyle.Sizable;
rd.addMessage("Input path = " + InPath);
rd.addMessage("Total Sample size = " + n.ToString());
rd.addMessage("\nLabel |Compare V1-V2 |N |Dif |T-Stat |P-Value ");
rd.addMessage("-".PadRight(83,'-'));
KMeansClusterCollection gCol = kmeans.Clusters;
for (int i = 0; i < gCol.Count; i++)
{
string l = getValue(Labels[i],8);
KMeansCluster gClust = gCol[i];
double[] mns = gClust.Mean;
double[] var = new double[mns.Length];
double nSample = gClust.Proportion * N;
if (nSample <= 1) continue;
double seAdjust = Math.Sqrt(2*1/nSample);
for (int j = 0; j < mns.Length; j++)
{
var[j] = gClust.Covariance[j, j];
}
int cnt = 1;
for (int j = 0; j < mns.Length-1; j++)
{
for (int k = cnt; k < mns.Length; k++)
{
string fN1 = getValue(VariableFieldNames[j],12);
string fN2 = getValue(VariableFieldNames[k],12);
double mD = mns[j] - mns[k];
double pSD = Math.Sqrt((var[j] + var[k]) / 2);
double se = pSD * seAdjust;
double tStat = mD / se;
Accord.Statistics.Distributions.Univariate.TDistribution tDist = new Accord.Statistics.Distributions.Univariate.TDistribution(2*nSample-2);
double cdf = tDist.DistributionFunction(tStat);
double pValue = 0;
if (tStat>0)
{
pValue = (1 - cdf) * 2;
}
else
{
pValue = (cdf * 2);
}
string pValueS = pValue.ToString();
if (pValue < 0.0001) pValueS = "p < 0.0001";
string ln = l + "|" + fN1 + "-" + fN2 + "| " + getValue(nSample.ToString(), 6) + " | " + getValue(mD.ToString(), 6) + " | " + getValue(tStat.ToString(), 6) + " | " + getValue(pValueS,10);
rd.addMessage(ln);
}
cnt += 1;
}
}
rd.addMessage("-".PadRight(83, '-'));
rd.enableClose();
rd.Show();
}
public double[] computeNew(object category)
{
string cat = category.ToString();
int catIndex = lbl.IndexOf(cat);
int np = ((VariableFieldNames.Length * VariableFieldNames.Length) - VariableFieldNames.Length) / 2;
double[] pValues = new double[np];
if (catIndex == -1) return pValues;
KMeansClusterCollection gCol = kmeans.Clusters;
KMeansCluster gClust = gCol[catIndex];
double[] mns = gClust.Mean;
double[] var = new double[mns.Length];
double nSample = gClust.Proportion * N;
double seAdjust = Math.Sqrt(2 * 1 / nSample);
for (int j = 0; j < mns.Length; j++)
{
var[j] = gClust.Covariance[j, j];
}
int cnt = 1;
int pCnt = 0;
for (int j = 0; j < mns.Length-1; j++)
{
for (int k = cnt; k < mns.Length; k++)
{
double mD = mns[j] - mns[k];
double pSD = Math.Sqrt((var[j] + var[k]) / 2);
double se = pSD * seAdjust;
double tStat = mD / se;
Accord.Statistics.Distributions.Univariate.TDistribution tDist = new Accord.Statistics.Distributions.Univariate.TDistribution(2*nSample-2);
double cdf = tDist.DistributionFunction(tStat);
double pValue = 0;
if (tStat>0)
{
pValue = (1 - cdf) * 2;
}
else
{
pValue = (cdf * 2);
}
pValues[pCnt] = pValue;
pCnt++;
}
cnt += 1;
}
return pValues;
}
new public void getReport()
{
if (cateDic.Count < 1)
{
buildModel();
}
rd = new Forms.RunningProcess.frmRunningProcessDialog(false);
rd.Text = "Paired T-Test Results";
rd.TopLevel = true;
rd.pgbProcess.Visible = false;
rd.FormBorderStyle = System.Windows.Forms.FormBorderStyle.Sizable;
rd.addMessage("Input path = " + InPath);
rd.addMessage("Total Sample size = " + n.ToString());
rd.addMessage("\nLabel |Compare V1-V2 |N |Dif |T-Stat |P-Value ");
rd.addMessage("-".PadRight(83, '-'));
for (int i = 0; i < lbl.Count; i++)
{
string labelVl = Labels[i];
string l = getValue(labelVl, 8);
int gN = cateDic[labelVl];
if (gN == 1)
{
continue;
}
double[] s = sumX[i];
double[] s2 = sumX2[i];
double[] mns = (from double d in s select d / gN).ToArray();
//Console.WriteLine("Means = " + mns.Length.ToString());
double[] ses = getSe(s, s2, gN);
//Console.WriteLine("Se = " + ses.Length.ToString());
double nSample = gN;
int cnt = 1;
int sCnt = 0;
for (int j = 0; j < VariableFieldNames.Length - 1; j++)
{
for (int k = cnt; k < VariableFieldNames.Length; k++)
{
string fN1 = getValue(VariableFieldNames[j], 12);
string fN2 = getValue(VariableFieldNames[k], 12);
double mD = mns[sCnt];
double se = ses[sCnt];
double tStat = mD / se;
//Console.WriteLine(tStat.ToString());
Accord.Statistics.Distributions.Univariate.TDistribution tDist = new Accord.Statistics.Distributions.Univariate.TDistribution(nSample - 1);
double cdf = tDist.DistributionFunction(tStat);
double pValue = 0;
if (tStat > 0)
{
pValue = (1 - cdf) * 2;
}
else
{
pValue = (cdf * 2);
}
string pValueS = pValue.ToString();
if (pValue < 0.0001)
{
pValueS = pValueS = "p < 0.0001";
}
string ln = l + "|" + fN1 + "-" + fN2 + "| " + getValue(nSample.ToString(), 6) + " | " + getValue(mD.ToString(), 6) + " | " + getValue(tStat.ToString(), 6) + " | " + getValue(pValueS, 10);
rd.addMessage(ln);
sCnt += 1;
}
cnt += 1;
}
}
rd.addMessage("-".PadRight(83, '-'));
rd.enableClose();
rd.Show();
}
public static void PairedTTestPValues(double[] popMeans, double[,] popVarCov, double[] sampMeans, double[,] sampVarCov, out double meanPvalue, out double varPvalue)
{
double n = popMeans.Length;
meanPvalue = 0;
varPvalue = 0;
double sumM = 0;
double sumV = 0;
double sumM2 = 0;
double sumV2 = 0;
for (int i = 0; i < n; i++)
{
double m1 = popMeans[i];
double m2 = sampMeans[i];
double dm = m1 - m2;
double v1 = popVarCov[i, i];
double v2 = sampVarCov[i, i];
double dv = v1 - v2;
sumM += dm;
sumV += dv;
sumM2 += dm * dm;
sumV2 += dv * dv;
}
double mM = sumM / n;
double mV = sumV / n;
double seM = Math.Sqrt((sumM2 - ((sumM * sumM) / n)) / n) / Math.Sqrt(n);
double seV = Math.Sqrt((sumV2 - ((sumV * sumV) / n)) / n) / Math.Sqrt(n);
double mTstat = mM / seM;
double vTstat = mV / seV;
Accord.Statistics.Distributions.Univariate.TDistribution tDist = new Accord.Statistics.Distributions.Univariate.TDistribution(n - 1);
double mCdf = tDist.DistributionFunction(mTstat);
double vCdf = tDist.DistributionFunction(vTstat);
if (mTstat > 0)
{
meanPvalue = (1 - mCdf) * 2;
}
else
{
meanPvalue = mCdf * 2;
}
if (vTstat > 0)
{
varPvalue = (1 - vCdf) * 2;
}
else
{
varPvalue = vCdf * 2;
}
}
public void getReport()
{
if (kmeans == null)
{
buildModel();
}
rd = new Forms.RunningProcess.frmRunningProcessDialog(false);
rd.Text = "Independent T-Test Results";
rd.TopLevel = true;
rd.pgbProcess.Visible = false;
rd.FormBorderStyle = System.Windows.Forms.FormBorderStyle.Sizable;
rd.addMessage("Input path = " + InPath);
rd.addMessage("Total Sample size = " + n.ToString());
rd.addMessage("\nLabel |Compare V1-V2 |N |Dif |T-Stat |P-Value ");
rd.addMessage("-".PadRight(83, '-'));
KMeansClusterCollection gCol = kmeans.Clusters;
for (int i = 0; i < gCol.Count; i++)
{
string l = getValue(Labels[i], 8);
KMeansCluster gClust = gCol[i];
double[] mns = gClust.Mean;
double[] var = new double[mns.Length];
double nSample = gClust.Proportion * N;
if (nSample <= 1)
{
continue;
}
double seAdjust = Math.Sqrt(2 * 1 / nSample);
for (int j = 0; j < mns.Length; j++)
{
var[j] = gClust.Covariance[j, j];
}
int cnt = 1;
for (int j = 0; j < mns.Length - 1; j++)
{
for (int k = cnt; k < mns.Length; k++)
{
string fN1 = getValue(VariableFieldNames[j], 12);
string fN2 = getValue(VariableFieldNames[k], 12);
double mD = mns[j] - mns[k];
double pSD = Math.Sqrt((var[j] + var[k]) / 2);
double se = pSD * seAdjust;
double tStat = mD / se;
Accord.Statistics.Distributions.Univariate.TDistribution tDist = new Accord.Statistics.Distributions.Univariate.TDistribution(2 * nSample - 2);
double cdf = tDist.DistributionFunction(tStat);
double pValue = 0;
if (tStat > 0)
{
pValue = (1 - cdf) * 2;
}
else
{
pValue = (cdf * 2);
}
string pValueS = pValue.ToString();
if (pValue < 0.0001)
{
pValueS = "p < 0.0001";
}
string ln = l + "|" + fN1 + "-" + fN2 + "| " + getValue(nSample.ToString(), 6) + " | " + getValue(mD.ToString(), 6) + " | " + getValue(tStat.ToString(), 6) + " | " + getValue(pValueS, 10);
rd.addMessage(ln);
}
cnt += 1;
}
}
rd.addMessage("-".PadRight(83, '-'));
rd.enableClose();
rd.Show();
}