pluginVariation: Plugin Variation

In countprop: Calculate Model-Based Metrics of Proportionality on Count-Based Compositional Data

Plugin Variation

Description

Estimates the variation matrix of count-compositional data based on a the same approximation used in logitNormalVariation() only for this function it uses empirical estimates of mu and Sigma. Also performs zero-imputation using cmultRepl() from the zCompositions package.

Usage

pluginVariation(
  counts,
  type = c("standard", "phi", "phis", "rho"),
  order = c("second", "first"),
  impute.zeros = TRUE,
  ...
)

Arguments

counts	Matrix of counts; samples are rows and features are columns.
type	Type of variation metric to be calculated: standard, phi, phis (a symmetrical version of phi), rho, or logp (the variance-covariance matrix of log-transformed proportions).
order	The order of the Taylor-series approximation to be used in the estimation
impute.zeros	If TRUE, then cmultRepl() from the zCompositions package is used to impute zero values in the counts matrix.
...	Optional arguments passed to zero-imputation function cmultRepl()

Value

An estimate of the requested metric of proportionality.

Examples

data(singlecell)

pluginVariation(singlecell)
pluginVariation(singlecell, type="phi")
pluginVariation(singlecell, type="rho")

countprop documentation built on Aug. 18, 2023, 9:06 a.m.