read.CMData

name of file with data. The data in the file
  should be structured as described above.

file

logical indicator of whether a
  cluster size variable is present in the file

with.clustersize

logical indicator of whether a frequency
  variable is present in the file

with.freq

additonal arguments passed to
  <code><a href="/link/read.table?package=CorrBin&version=1.4&to=utils" rd-options="utils" data-mini-rdoc="utils::read.table">read.table</a></code>

A convenience function to read data from specially
structured file directly into a <code>CMData</code> object. There
are two basic data format options: etiher the counts of
responses of all categories are given (and the cluster size
is the sum of these counts), or the total cluster size is
given with the counts of all but one category. The first
column should always give the treatment group, then either
the counts for each category (first option, chosen by
setting <code>with.clustersize = FALSE</code>), or the size of
the cluster followed by the counts for all but one category
(second option, chosen by setting <code>with.clustersize =
TRUE</code>). Optionally, a last column could give the number of
times the given combination occurs in the data.

This package implements non-parametric analyses for clustered
    binary data. The elements of the cluster are assumed exchangeable, and
    identical joint distribution (also known as marginal compatibility, or
    reproducibility) is assumed for clusters of different sizes. A trend test
    based on stochastic ordering is implemented.

read.CMData: Read data from external file into a CMData object

Description

Usage

Arguments

Value

See Also