fitNull fits the null distribution to a set of negative controls using Markov Chain Monte
Carlo (MCMC).
fitMcmcNull(logRr, seLogRr, iter = 1e+05)Arguments
- logRr
A numeric vector of effect estimates on the log scale
- seLogRr
The standard error of the log of the effect estimates. Hint: often the standard error = (log(<lower bound 95 percent confidence interval>) - log(<effect estimate>))/qnorm(0.025)
- iter
Number of iterations of the MCMC.
Value
An object of type mcmcNull containing the mean and standard deviation (both on the log
scale) of the null distribution, as well as the MCMC trace.
Details
This is an experimental function for computing the 95 percent credible interval of a calibrated p-value using Markov-Chain Monte Carlo (MCMC).
Examples
if (FALSE) {
data(sccs)
negatives <- sccs[sccs$groundTruth == 0, ]
null <- fitMcmcNull(negatives$logRr, negatives$seLogRr)
null
plotMcmcTrace(null)
positive <- sccs[sccs$groundTruth == 1, ]
calibrateP(null, positive$logRr, positive$seLogRr)
}