/** Compute the log likelihood that these samples came from the
* specified distribution shifted by the parameter theta.
* @param theta the parameter of the PMF, f_theta(x)
* @param samples the samples
* @param pmf the probability mass function
* @return the log likelihood
*/
static pair<double, unsigned>
computeLikelihood(int theta, const Histogram& samples, const PMF& pmf)
{
double likelihood = 0;
unsigned nsamples = 0;
for (Histogram::const_iterator it = samples.begin();
it != samples.end(); ++it) {
double p = pmf[it->first + theta];
unsigned n = it->second;
likelihood += n * log(p);
if (p > pmf.minProbability())
nsamples += n;
}
return make_pair(likelihood, nsamples);
}
/** Estimate the distance between two contigs using the difference of
* the population mean and the sample mean.
* @param numPairs [out] the number of pairs that agree with the
* expected distribution
* @return the estimated distance
*/
static int estimateDistanceUsingMean(
const std::vector<int>& samples, const PMF& pmf,
unsigned& numPairs)
{
Histogram h(samples.begin(), samples.end());
int d = (int)round(pmf.mean() - h.mean());
// Count the number of samples that agree with the distribution.
unsigned n = 0;
for (Histogram::const_iterator it = h.begin();
it != h.end(); ++it)
if (pmf[it->first + d] > pmf.minProbability())
n += it->second;
numPairs = n;
return d;
}
