/*
* perform single tail F test!
* The larger variance should always be placed in the numerator
*/
public static boolean isEqualVariance(
double variance1,
double variance2,
double degOfFreedom1,
double degOfFreedom2,
double[] stats) {
/*
*
The hypothesis that the two variances are equal is rejected if
F>Falpha,N1-1,N2-1 for an upper one-tailed test
F<F1-alpha,N1-1,N2-1 for a lower one-tailed test
*/
if (stats == null || stats.length < 4) {
throw new IllegalStateException();
}
double alpha = 0.05;
double numVar;
double denVar;
double numDf;
double denDf;
if (variance1 > variance2) {
numVar = variance1;
numDf = degOfFreedom1;
denVar = variance2;
denDf = degOfFreedom2;
} else {
numVar = variance2;
numDf = degOfFreedom2;
denVar = variance1;
denDf = degOfFreedom1;
}
FDistribution fd = new FDistribution(numDf, denDf);
double F = numVar / denVar;
double pOneTail = 1 - fd.cumulativeProbability(F); // good
double fCritical = fd.inverseCumulativeProbability(1 - alpha);
stats[0] = F;
stats[1] = fCritical;
if (display_stats) {
System.out.println("F: " + F + "\tfCritical: " + fCritical);
}
if (F < fCritical) {
/*
* If F<Fcrit then automatically p>0.05. Correspondingly, if F>=Fcrit then automatically p<=0.05.
*/
if (!(pOneTail > 0.05)) {
System.out.println("StatAnalyzer.java -- isEqualVariance() -- something's wrong!!");
System.exit(0);
}
return true;
} else {
return false;
}
}
protected static void test(
int d,
int p,
Integer probeId,
double[] x,
double[] originalGenotypes,
double varianceX,
double varianceY,
double meanY,
boolean[] includeExpressionSample,
int sampleCount,
double[][] rawData,
double[][] covariateRawData,
Result r,
WorkPackage wp,
boolean metaAnalyseModelCorrelationYHat,
boolean metaAnalyseInteractionTerms,
boolean determinefoldchange) {
final double[] y;
double[][] covariates = covariateRawData;
if (x.length != sampleCount) {
y = new double[x.length];
int itr = 0;
double sum = 0;
double[] tmpY = rawData[probeId];
// recalculate mean and variance
for (int s = 0; s < sampleCount; s++) {
if (includeExpressionSample[s]) {
y[itr] = tmpY[s];
sum += y[itr];
itr++;
}
}
meanY = sum / itr;
if (meanY != 0) {
for (int i = 0; i < y.length; ++i) {
y[i] = y[i] - meanY;
}
meanY = 0;
}
varianceY = Descriptives.variance(y, meanY);
if (covariates != null) {
int covariateitr = 0;
covariates =
new double[covariateRawData.length][0]; // take only the first covariate for now..
for (int covariate = 0; covariate < covariateRawData.length; covariate++) {
covariates[covariate] = new double[x.length];
for (int s = 0; s < sampleCount; s++) {
if (includeExpressionSample[s]) {
covariates[covariate][covariateitr] = covariateRawData[covariate][s];
covariateitr++;
}
}
}
}
} else {
y = new double[x.length];
System.arraycopy(rawData[probeId], 0, y, 0, x.length);
}
double meanX = JSci.maths.ArrayMath.mean(x);
if (meanY > 0.000000001d
|| meanY < -0.00000001d
|| meanX > 0.000000001d
|| meanX < -0.00000001d) {
double res = 0;
for (double y2 : y) {
res += y2;
}
res /= y.length;
double res2 = 0;
for (double x2 : x) {
res2 += x2;
}
res2 /= x.length;
throw new RuntimeException(
"Error in eQTL calculation, mean of X or Y was not 0, specified mean y: "
+ meanY
+ " and really is: "
+ res
+ ", specifief mean x: "
+ meanX
+ " and really is: "
+ res2);
}
if (varianceY == 0) {
r.zscores[d][p] = Double.NaN;
r.correlations[d][p] = Double.NaN;
} else if (covariates != null) {
// TODO: what to do when there are multiple covariates involved?
double[][] olsXFullWithInteraction =
new double[x.length]
[3]; // With interaction term, linear model: y ~ a * SNP + b * CellCount + c + d * SNP
// * CellCount
for (int i = 0; i < x.length; i++) {
double xi = x[i];
double covi = covariates[0][i];
olsXFullWithInteraction[i][0] = xi;
olsXFullWithInteraction[i][1] = covi;
olsXFullWithInteraction[i][2] = covi * xi;
}
OLSMultipleLinearRegression regressionFullWithInteraction = new OLSMultipleLinearRegression();
regressionFullWithInteraction.newSampleData(y, olsXFullWithInteraction);
if (metaAnalyseModelCorrelationYHat) {
double[] regressionParameters =
regressionFullWithInteraction.estimateRegressionParameters();
double[] yInferred = new double[y.length];
for (int s = 0; s < y.length; s++) {
yInferred[s] = regressionParameters[0];
for (int a = 0; a < 3; a++) {
yInferred[s] += regressionParameters[a + 1] * olsXFullWithInteraction[s][a];
}
}
SpearmansCorrelation spearman = new SpearmansCorrelation();
double correlationspearman = spearman.correlation(y, yInferred);
double zScore = Correlation.convertCorrelationToZScore(y.length, correlationspearman);
r.zscores[d][p] = zScore;
r.correlations[d][p] = correlationspearman;
r.beta[d][p] = regressionFullWithInteraction.calculateRSquared();
} else if (metaAnalyseInteractionTerms) {
double[] regressionParameters =
regressionFullWithInteraction.estimateRegressionParameters();
double[] regressionStandardErrors =
regressionFullWithInteraction.estimateRegressionParametersStandardErrors();
double betaInteraction = regressionParameters[3];
double seInteraction = regressionStandardErrors[3];
double tInteraction = betaInteraction / seInteraction;
double pValueInteraction;
double zScoreInteraction;
StudentT tDistColt = new cern.jet.random.tdouble.StudentT(x.length - 4, randomEngine);
if (tInteraction < 0) {
pValueInteraction = tDistColt.cdf(tInteraction);
if (pValueInteraction < 2.0E-323) {
pValueInteraction = 2.0E-323;
}
zScoreInteraction = cern.jet.stat.tdouble.Probability.normalInverse(pValueInteraction);
} else {
pValueInteraction = tDistColt.cdf(-tInteraction);
if (pValueInteraction < 2.0E-323) {
pValueInteraction = 2.0E-323;
}
zScoreInteraction = -cern.jet.stat.tdouble.Probability.normalInverse(pValueInteraction);
}
pValueInteraction *= 2;
r.zscores[d][p] = zScoreInteraction;
r.correlations[d][p] = regressionFullWithInteraction.calculateRSquared();
r.se[d][p] = seInteraction;
r.beta[d][p] = betaInteraction;
// if (rConnection != null) {
// try {
// if (rConnection.isConnected()) {
// rConnection.assign("y", y);
// rConnection.assign("x", x);
// rConnection.assign("z", covariates[0]);
// rConnection.voidEval("interaction <- x*z");
// rConnection.voidEval("m <- lm(y ~ x + z + interaction)");
// rConnection.voidEval("modelsummary <- summary(m)");
// double betaInteractionR =
// rConnection.eval("modelsummary$coefficients[4,1]").asDouble();
// rConnection.voidEval("m2 <- sqrt(diag(vcovHC(m, type =
// 'HC0')))");
// double seInteractionRCorrected =
// rConnection.eval("as.numeric(m2[4])").asDouble();
// double tInteraction = betaInteractionR /
// seInteractionRCorrected;
// double pValueInteraction = 1;
// double zScoreInteraction = 0;
// DRand randomEngine = new
// cern.jet.random.tdouble.engine.DRand();
// StudentT tDistColt = new
// cern.jet.random.tdouble.StudentT(x.length - 4, randomEngine);
// if (tInteraction < 0) {
// pValueInteraction = tDistColt.cdf(tInteraction);
// if (pValueInteraction < 2.0E-323) {
// pValueInteraction = 2.0E-323;
// }
// zScoreInteraction =
// cern.jet.stat.tdouble.Probability.normalInverse(pValueInteraction);
// } else {
// pValueInteraction = tDistColt.cdf(-tInteraction);
// if (pValueInteraction < 2.0E-323) {
// pValueInteraction = 2.0E-323;
// }
// zScoreInteraction =
// -cern.jet.stat.tdouble.Probability.normalInverse(pValueInteraction);
// }
// randomNumberGenerator.zscores[d][p] = zScoreInteraction;
// randomNumberGenerator.correlations[d][p] = betaInteractionR;
//
// // int dfresiduals =
// rConnection.eval("m$df.residual").asInteger();
//// double[] coeff =
// rConnection.eval("m$coefficients").asDoubles(); // intercept: 0, x: 1, z: 2, zx: 3
//// double fstat =
// rConnection.eval("as.numeric(modelsummary$fstatistic['value'])").asDouble();
//// double fstatdf =
// rConnection.eval("as.numeric(modelsummary$fstatistic['numdf'])").asDouble();
//// double fstatdferr =
// rConnection.eval("as.numeric(modelsummary$fstatistic['dendf'])").asDouble();
//// double rsquared =
// rConnection.eval("as.numeric(modelsummary$r.squared)").asDouble();
//// double seInteractionR =
// rConnection.eval("modelsummary$coefficients[4,2]").asDouble();
// } else {
// System.err.println("ERROR: R is not connected.");
// }
// } catch (REngineException ex) {
//
// Logger.getLogger(CalculationThread.class.getName()).log(Level.SEVERE, null, ex);
// } catch (REXPMismatchException ex) {
//
// Logger.getLogger(CalculationThread.class.getName()).log(Level.SEVERE, null, ex);
// }
// }
} else {
double residualSS = regressionFullWithInteraction.calculateResidualSumOfSquares();
double r2 = regressionFullWithInteraction.calculateRSquared();
// calculate F statistic for the significance of the model
double totalSS = regressionFullWithInteraction.calculateTotalSumOfSquares();
double modelSS = totalSS - residualSS;
double dfmodel = olsXFullWithInteraction[0].length;
double dferror = x.length - dfmodel - 1;
double msm = modelSS / dfmodel;
double mse = residualSS / dferror;
double f = msm / mse;
FDistribution fDist =
new org.apache.commons.math3.distribution.FDistribution(dfmodel, dferror);
double pvalmodel = 1 - fDist.cumulativeProbability(f);
double zscore = 0;
if (pvalmodel == 1d) {
zscore = 0;
} else if (pvalmodel == 0d) {
pvalmodel = 1e-16;
}
try {
zscore = ZScores.pToZ(pvalmodel);
} catch (IllegalArgumentException e) {
System.out.println(f + "\t" + pvalmodel + "\t" + zscore);
for (int i = 0; i < x.length; i++) {
System.out.println(i + "\t" + x[i] + "\t" + y[i] + "\t" + covariates[0][i]);
}
System.exit(-1);
}
r.zscores[d][p] = zscore;
r.correlations[d][p] = r2;
}
} else {
// Calculate correlation coefficient:
double stdevy = Math.sqrt(varianceY);
double stdevx = Math.sqrt(varianceX);
// double stdevy = JSci.maths.ArrayMath.standardDeviation(y);
// double stdevx = JSci.maths.ArrayMath.standardDeviation(x);
double correlation = Correlation.correlateMeanCenteredData(x, y, (stdevy * stdevx));
if (correlation >= -1 && correlation <= 1) {
double zScore = Correlation.convertCorrelationToZScore(x.length, correlation);
double[] xcopy = new double[x.length];
// double meany = JSci.maths.ArrayMath.mean(y);
for (int i = 0; i < y.length; i++) {
y[i] /= stdevy;
xcopy[i] = x[i] / stdevx;
}
// meany = JSci.maths.ArrayMath.mean(y);
// double meanxCopy = JSci.maths.ArrayMath.mean(xcopy);
// calculateRegressionCoefficients(xcopy, meanxCopy, y, meany,
// randomNumberGenerator, d, p);
calculateRegressionCoefficients(xcopy, y, r, d, p);
if (determinefoldchange) {
determineFoldchange(originalGenotypes, y, r, d, p, wp);
}
r.zscores[d][p] = zScore;
r.correlations[d][p] = correlation;
} else {
// Ususally if the genotype variance is very low
System.err.println(
"Error! correlation invalid: "
+ correlation
+ "; genotype variance = "
+ varianceX
+ "; expression variance = "
+ varianceY);
r.zscores[d][p] = Double.NaN;
r.correlations[d][p] = Double.NaN;
// System.exit(-1);
}
}
}