uniprobs

Calculates the marginal probability of each event type for exchangeable correlated multinomial
data based on joint probability estimates calculated by the <code>jointprobs</code> function.

Implements non-parametric analyses for clustered
binary and multinomial 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.
Szabo A, George EO. (2010) <doi:10.1093/biomet/asp077>;
George EO, Cheon K, Yuan Y, Szabo A (2016) <doi:10.1093/biomet/asw009>.

Aniko Szabo

CorrBin

Nonparametrics with Clustered Binary and Multinomial Data

uniprobs function

<dl><dt>jp</dt>
<dd>the output of <code>jointprobs</code> - a list of joint probability arrays by treatment</dd>
<dt>type</dt>
<dd>one of c("averaged","cluster","mc") - the type of joint probability. By default,
the <code>type</code> attribute of <code>jp</code> is used.</dd></dl>

Arguments

Extract univariate marginal probabilities from joint probability arrays — uniprobs

<dl>

<dt>jp</dt>
<dd>the output of <code>jointprobs</code> - a list of joint probability arrays by treatment</dd>


<dt>type</dt>
<dd>one of c("averaged","cluster","mc") - the type of joint probability. By default,
the <code>type</code> attribute of <code>jp</code> is used.</dd>

</dl>

uniprobs: Extract univariate marginal probabilities from joint probability arrays

Description

Usage

Value

Arguments

See Also

Examples