normalizeScale {limma} | R Documentation |
Performs scale normalization of an M-value matrix or an A-value matrix across a series of arrays.
Users do not normally need to call these functions directly - use normalizeBetweenArrays
instead.
normalizeMedianDeviations(x) normalizeMedians(x)
x |
numeric matrix |
If x
is a matrix of log-ratios of expression (M-values) then normalizeMedianDeviations
is very similar to scaling to equalize the median absolute deviation (MAD) as in Yang et al (2001, 2002).
Here the median-absolute value is used for preference to as to not re-center the M-values.
normalizeMedians
is used for A-values of overall expression.
normalizeMedianDeviations
produces a numeric matrix of the same size as that input which has been scaled so that each column as the same median-absolute value.
normalizeMedians
produces a numeric matrix which has been scaled so that each column has the same median-value.
Gordon Smyth
An overview of LIMMA functions for normalization is given in 4.Normalization.
M <- cbind(Array1=rnorm(10),Array2=2*rnorm(10)) normalizeMedianDeviations(M) A <- cbind(Array1=rlnorm(10),Array2=2*rlnorm(10)) normalizeMedians(A)