assessQuality: Quality assessment for cleaning procedures.

In PeteHaitch/RUVcorr: Removal of unwanted variation for gene-gene correlations and related analysis.

Description

assessQuality allows to assess the quality of cleaning procedures in the context of correlations when the true underlying correlation structure is known.

Usage

assessQuality(est, true, index = "all", methods = c("all", "fnorm",
  "wrong.sign"))

Arguments

est	A matrix of estimated gene expression values.
true	A matrix of true correlations.
index	A vector of indices of genes to be included in the assessment; if index="all" all genes are considered.
methods	The method used for quality assessment; if method="fnorm" the Frobenius norm is used; if method="wrong.sign" the percentage of wrongly estimated signs is calculated if method="all" both are calculated.

Details

The Frobenius norm used for assessQuality has the following structure

F=\frac{\|E-T\|^2}{s}

Here, the parameter E and the parameter T denote the lower triangles of the estimated and true correlation matrices, respectively. The parameter s denotes the number of elements in E and T.

Value

assessQuality returns a vector of the requested quality assessments.

Author(s)

Saskia Freytag

Examples

Y<-simulateGEdata(500, 500, 10, 2, 5, g=NULL, Sigma.eps=0.1, 250, 100, check.input=FALSE)
assessQuality(Y$Y, Y$Sigma, index=1:100, methods="wrong.sign")
assessQuality(Y$Y, Y$Sigma, index=1:100, method="fnorm")

PeteHaitch/RUVcorr documentation built on May 8, 2019, 1:31 a.m.