permindex: Permutation Index
In predictmeans: Predicted Means for Linear and Semiparametric Models

permindex

R Documentation

Permutation Index

Description

This function obtains permutation index for a dataset.

Usage

permindex(data, block=NULL, group=NULL, nsim=4999, seed)

Arguments

`data`	Data object used in the `model` fitting.
`block`	Name (in "quotes") for the blocking factor in the `data`.
`group`	Name (in "quotes") for the group factor in the `data`.
`nsim`	The number of permutations. The default is 4999.
`seed`	Specify a random number generator seed, for reproducible results.

Value

A matrix has 'nsim' columns of permuted index.

Author(s)

Dongwen Luo, Siva Ganesh and John Koolaard

Examples

  library(predictmeans)
  block <- rep(1:3, each=12)
  group <- rep(rep(1:3, each=4), 3)
  data <- data.frame(block, group)
  cbind(data, permindex(data, block="block", group="group", nsim=5))  
                        # Permute group as a whole within each block first, 
                        # then permute obs within each group.
  cbind(data, permindex(data, block="block",  nsim=5)) 
                        # Permute obs within each block only.
  cbind(data, permindex(data, group="group", nsim=5)) 
                        # Permute groups as a whole block first, 
                        # then permute obs within each group.
  cbind(data, permindex(data, nsim=5))  # Free permutation.

predictmeans documentation built on May 29, 2024, 9:49 a.m.