DCMS: De-correlated Composite of Multiple Signals (DCMS)

In NESCent/MINOTAUR: MultIvariate visualisatioN and OuTlier Analysis Using R

Description

Calculates the DCMS for each row (locus, SNP) in the data frame. Data are subset prior to calculating distances (see details).

Usage

DCMS(dfv, column.nums = 1:ncol(dfv), subset = 1:nrow(dfv), S = NULL, dfp,
  column.nums.p = 1:ncol(dfp))

Arguments

dfv	a data frame containing observations in rows and raw statistics in columns.
column.nums	indexes the columns of dfv that contain raw statistics.
subset	index the rows of the data frame that will be used to calculate the covariance matrix S (unless specified manually).
S	the covariance matrix used to account for correlation between observations in the DCMS calculation. Leave as NULL to use the ordinary covariance matrix calculated using cov(dfv[subset,column.nums],use="pairwise.complete.obs").
dfp	a data frame containing observations in rows and p-values in columns.
column.nums.p	indexes the columns of dfp that contain p-values.

Details

The selected columns of the dfv data frame (i.e. the columns specified by column.nums) should contain the raw test statistics, while the selected columns of the dfp data frame (i.e. the columns specified by column.nums.p) should contain the corresponding p-values. If the same data frame contains both raw statistics and p-values then this should be passed in as both dfv and dfp, with only the selected columns changing. The covariance matrix used in the DCMS calculation can be specified directly through the argument S, or if S=NULL then this matrix is calculated directly from selected rows and columns of dfv.

Author(s)

Robert Verity [e-mail]

NESCent/MINOTAUR documentation built on May 7, 2019, 6:01 p.m.