up_max_bb: EM algorithm for over-dispersed mixture model.
In dcgerard/updogAlpha: Using Parental Data for Offspring Genotyping

EM algorithm for over-dispersed mixture model.

up_max_bb(ocounts, osize, qarray, r1vec, r2vec, pk, pival = 0.99,
  out_mu = 0.5, out_rho = 0.8, rho = 0.001, est_fudge = TRUE,
  tol = 10^-4, itermax = 1000, update_geno = FALSE,
  update_pival = FALSE, update_outlier = FALSE, update_rho = FALSE)

`ocounts`	A vector of non-negative integers. The ith element is the number of reads of the reference allele in the ith child.
`osize`	A vector of positive integers. The ith element is the total number of reads for the ith child.
`qarray`	An three-way array of proportions. The (i, j, k)th element is the probability of an offspring having k - 1 reference alleles given that parent 1 has i - 1 refrerence alleles and parent 2 has j - 1 reference alleles. Each dimension of the array is `ploidy + 1`.
`r1vec`	A vector of prior probabilities whose ith element is the prior probability that parent 1 has i -1 copies of allele A.
`r2vec`	A vector of prior probabilities whose ith element is the prior probability that parent 2 has i -1 copies of allele A.
`pk`	The parameter space. Should all be between 0 and 1.
`pival`	A fudge factor. The probability of not begin a mistake. Estimated if `est_fudge = TRUE`. Set to 0.99. Only used if `est_fudge = TRUE`.
`out_mu`	The outlier mean.
`out_rho`	The outlier overdispersion parameter.
`rho`	The overdispersion parameter. Needs to be between 0 and 1. If it is exactly 0, you should be using `updog_maximize`.
`est_fudge`	A logical. Should we estimate the fudge factor `TRUE` or not `FALSE`?
`tol`	A positive numeric. The tolerance for the stopping criterion.
`itermax`	A positive integer. The maximum number of iterations to run in the EM.
`update_geno`	A logical. Update the parental genotypes?
`update_pival`	A logical. Should we update the mixing proportion (`TRUE`) or not (`FALSE`)?
`update_outlier`	A logical. Should we update the outlier distribution (`TRUE`) or not (`FALSE`)?
`update_rho`	A logical. Should we we update the overdispersion parameter (`TRUE`) or not (`FALSE`)?