mclogit_control: Control Parameters for the Fitting Process

In mclogit: Multinomial Logit Models, with or without Random Effects or Overdispersion

Control Parameters for the Fitting Process

Description

mclogit.control returns a list of default parameters that control the fitting process of mclogit.

Usage

mclogit.control(epsilon = 1e-08,
                maxit = 25, trace=TRUE)
mmclogit.control(epsilon = 1e-08,
                 maxit = 25, trace=TRUE,
                 trace.inner=FALSE,
                 avoid.increase = FALSE,
                 break.on.increase = FALSE,
                 break.on.infinite = FALSE,
                 break.on.negative = FALSE)

Arguments

epsilon	positive convergence tolerance ε; the iterations converge when |dev - devold|/(|dev| + 0.1) < ε.
maxit	integer giving the maximal number of IWLS or PQL iterations.
trace	logical indicating if output should be produced for each iteration.
trace.inner	logical; indicating if output should be produced for each inner iteration of the PQL method.
avoid.increase	logical; should an increase of the deviance be avoided by step truncation?
break.on.increase	logical; should an increase of the deviance be avoided by stopping the algorithm?
break.on.infinite	logical; should an infinite deviance stop the algorithm instead of leading to step truncation?
break.on.negative	logical; should a negative deviance stop the algorithm?

Value

A list.

mclogit documentation built on Oct. 29, 2022, 1:09 a.m.