mMsMatrix {PAA} | R Documentation |
Computes a reference minimum M statistic (n1 x n2)-matrix (mMs matrix).
mMsMatrix(x, y)
x |
integer, first dimension (i.e., number of samples in group 1) of the mMs matrix to be computed (mandatory). |
y |
integer, second dimension (i.e., number of samples in group 2) of the mMs matrix to be computed (mandatory). |
For feature preselection the "minimum M Statistic" (mMs) proposed by Love B. can
be used. The mMs is a univariate measure that is sensitive to population
subgroups. To avoid redundant mMs computations for a large number of features
(e.g., ca. 9500 features on ProtoArray v5) a reference matrix containing all
relevant mMs values can be precomputed. For this purpose, only two parameters
are needed: the number of samples in group 1 (n1
) and the number of
samples in group 2 (n2
). According to mMs definition for each matrix
element (i,m) a mMs value (= the probability of) for having m values in group 1
larger than the i-th largest value in group 2 is computed.
A (n1 x n2)-matrix containing all mMs values for group 1 and group 2.
To check whether a feature is more prevalent in group 1 or in group 2, PAA needs
both the mMs for having m values in group 1 larger than the i-th largest
element in group 2 as well as the mMs for having m values in group 2 larger than
the i-th largest element in group 1. Hence, always both must be computed:
mMsMatrix(n1,n2)
and mMsMatrix(n2,n1)
.
Michael Turewicz, michael.turewicz@rub.de
Love B: The Analysis of Protein Arrays. In: Functional Protein Microarrays in Drug Discovery. CRC Press; 2007: 381-402.
#exemplary computation for a group 1 comprising 10 arrays and a group 2 #comprising 12 arrays mMs.matrix1 <- mMsMatrix(x=10, y=12) mMs.matrix2 <- mMsMatrix(x=12, y=10)