fitZeroLogNormal: Compute the log fold-change estimates for the zero-inflated...

In metagenomeSeq: Statistical analysis for sparse high-throughput sequencing

Description

Run the zero-inflated log-normal model given a MRexperiment object and model matrix. Not for the average user, assumes structure of the model matrix.

Usage

fitZeroLogNormal(obj, mod, coef = 2, szero = TRUE, spos = TRUE)

Arguments

obj	A MRexperiment object with count data.
mod	The model for the count distribution.
coef	Coefficient of interest to grab log fold-changes.
szero	TRUE/FALSE, shrink zero component parameters.
spos	TRUE/FALSE, shrink positive component parameters.

Value

A list of objects including:

• logFC - the log fold-change estimates

• adjFactor - the adjustment factor based on the zero component

• se - standard error estimates

• fitln - parameters from the log-normal fit

• fitzero - parameters from the logistic fit

• zeroRidge - output from the ridge regression

• posRidge - output from the ridge regression

• tauPos - estimated tau^2 for positive component

• tauZero - estimated tau^2 for zero component

• exclude - features to exclude for various reasons, e.g. all zeros

• zeroExclude - features to exclude for various reasons, e.g. all zeros

See Also

cumNorm fitFeatureModel

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