mclogit.control

positive convergence tolerance $\epsilon$;
    the iterations converge when
    $|dev - dev_{old}|/(|dev| + 0.1) < \epsilon$.

epsilon

integer giving the maximal number of IWLS or PQL iterations.

maxit

logical indicating if output should be produced for each
    iteration.

trace

<code>mclogit.control</code> returns a list of default parameters
  that control the fitting process of <code>mclogit</code>.

This packages provides a function to estimate parameters for the
  mixed conditional logit model, or conditional logit with random effects.
  The current implementation of random effects is limited to 
  the PQL technique, which requires large cluster sizes.

mclogit.control: Control Parameters for the Fitting Process

Description

Usage

Arguments

Value