means.var {SharedHT2}R Documentation

Means and Variance

Description

Calculate the vector of group means and empirical variance/covariance matrix

Usage

 means.var(data, labels, subset, H0 = NULL, Var.Struct = NULL,
                 na.action = na.pass)

Arguments

data data frame containing the logged (base 2 or base 10) expression values in all arrays from the experiment. By default the variables are taken from the environment which EB.Anova is called from. Variable names should be chosen to be internally consistent in some searchable way. For example, if you have d=2 experimental groups (say treatment one versus control and treatment two versus control), and n=3 replicates in each group, you might choose names like: log2.grp1.n1, log2.grp2.n1, log2.grp1.n2, log2.grp2.n2, log2.grp1.n3, log2.grp2.n3 Notice that order that the names occur is irrelevent. In time course data the time point is the grouping variable. The rows should be named using the gene identifiers.
labels A character vector containing the group names, these being fragments of the variable names in the data argument supplied. In the example above, labels = c("log2.grp1", "log2.grp2")
subset an index vector indicating which rows should be used. (NOTE: If given, this argument must be named.)
H0 Character string specifying the null hypothesis. See the documentation for EB.Anova. This argument is tested to determine the minimum number of replicates neccesary and is used internally in order that rows deleted due to too many missing replicates during a call to EB.Anova are also deleted during an embedded call to this function. The user can either specify this argument or leave it unspecified.
Var.Struct Character string specifying the variance structure. See the documentation for EB.Anova. This argument is tested to determine the minimum number of replicates neccesary and is used internally in order that rows deleted due to too many missing replicates during a call to EB.Anova are also deleted during an embedded call to this function. The user can either specify this argument or leave it unspecified.
na.action Specify na.action = na.pass if your data contains NA's and you wish to treat them as missing at random. Otherwise, leave it unspecified. See the documentation for EB.Anova.

Value

A list containing two components

mean an Ngenes by d matrix representing the per gene group means
var a Ngenes by d*d matrix representing the per gene empirical variance covariance matrices

Note

Under the Wishart/Inverse Wishart Bayesian model, the expected value of the random per gene covariance matrix is equal to rate/(shape - 2*d - 2). Thus as a consistency check you can check the observed mean against the theoretical mean as in the following example.

Author(s)

Grant Izmirlian izmirlian@nih.gov

See Also

EB.Anova, EBfit, SimAffyDat, TopGenes, SimNorm.IG, SimMVN.IW, SimMVN.mxIW, SimOneNorm.IG, SimOneMVN.IW, SimOneMVN.mxIW

Examples

  data(SimAffyDat)
  fit.SimAffyDat <- EB.Anova(data=SimAffyDat, labels=c("log2.grp" %,% (1:2)),
                             H0="zero.means", Var.Struct = "general")
  mv.SimAffyDat <- EBfit(fit.SimAffyDat)
  mv.SimAffyDat$call[[1]] <- as.name("means.var")
  mv.SimAffyDat <- update(mv.SimAffyDat)

  d <- dim(mv.SimAffyDat$mean)[2]

  apply(mv.SimAffyDat$var, 2, FUN=mean)
  c(EBfit(fit.SimAffyDat)$rate/(EBfit(fit.SimAffyDat)$shape - 2*d - 2))

[Package SharedHT2 version 2.0 Index]