getNegativeLogLikelihoods: Calculate the negative log-likelihoods for the various...

In metagenomeSeq: Statistical analysis for sparse high-throughput sequencing

Description

Maximum-likelihood estimates are approximated using the EM algorithm where we treat mixture membership $delta_ij$ = 1 if $y_ij$ is generated from the zero point mass as latent indicator variables. The log-likelihood in this extended model is $(1-delta_ij) log f_count(y;mu_i,sigma_i^2 )+delta_ij log pi_j(s_j)+(1-delta_ij)log (1-pi_j (sj))$. The responsibilities are defined as $z_ij = pr(delta_ij=1 | data and current values)$.

Usage

getNegativeLogLikelihoods(z, countResiduals, zeroResiduals)

Arguments

z	Matrix (m x n) of estimate responsibilities (probabilities that a count comes from a spike distribution at 0).
countResiduals	Residuals from the count model.
zeroResiduals	Residuals from the zero model.

Value

Vector of size M of the negative log-likelihoods for the various features.

See Also

fitZig

metagenomeSeq documentation built on Nov. 8, 2020, 5:34 p.m.