parameters: Estimation of parameters for test equality of two normal...

In SourceSet: A Graphical Model Approach to Identify Primary Genes in Perturbed Biological Pathways

Estimation of parameters for test equality of two normal distributions

Description

The function estimates the parameters of two normal distributions. Both maximum likelihood estimates and shrinkage estimate of covariance matrices are supplied.

Usage

parameters(
  data,
  classes,
  shrink = TRUE,
  shrink.function = shrinkTEGS,
  shrink.param = list(probs = 0.05, type = "min")
)

Arguments

data	an expression matrix with colnames for variables and row names for samples
classes	a vector of length equal to the number of rows of data. It indicates the class (condition) of each statistical unit. Only two classes, labeled as 1 and 2, are allowed
shrink	boolean. if FALSE the maximum likelihood estimates are returned; if TRUE the shrinkage estimates are returned instead
shrink.function	function that implements the shrinkage method. It must return a list object with all the elements required as input arguments in testMeanVariance. Default is shrinkTEGS function.
shrink.param	additional parameters to pass as input arguments of the shrink function specified in the shrink.function.

Value

The function returns a list containing: three matrices with maximum likelihood or the shrinkage estimates (pooled, condition1 and condition2), and a list with the used parameters.

See Also

shrinkTEGS, testMeanVariance

Examples

if(require(mvtnorm)){
  ## Generate two random samples of size 50 from two multivariate normal distributions
  # sample size
  n<-50
  # true parameters of class 1 and class 2
  param.class1<-simulation$condition1
  param.class2<-simulation$condition2$`5`$`2`
  # simulated dataset
  data.class1<-rmvnorm(n = n,mean =param.class1$mu ,sigma =param.class1$S)
  data.class2<-rmvnorm(n = n,mean =param.class2$mu ,sigma=param.class2$S)
  data<-rbind(data.class1,data.class2)
  classes<-c(rep(1,nrow(data.class1)),rep(2,nrow(data.class2)))

  ## estimated parameters: maximum likelihood estimate
  est.param<-parameters(data = data,classes =classes ,shrink = FALSE)

  ## estimated parameters: regularized estimate
  est.param.shrink<-parameters(data = data,classes =classes ,shrink = TRUE)
  # tuning values and other info on shrinkage estimate
  str(est.param.shrink$shrink.info)
}

SourceSet documentation built on Nov. 21, 2022, 5:06 p.m.