0.8.5.3

Add 'vcov' method for 'mmclogit' objects.

0.8.5.2

Bugfix: Make 'update' work with missing dispersion= argument.

0.8.5.1

Corrects remaining cross-ref issues in the documentation. This is the version currently on CRAN.

0.8.5

• Added and documented simulate() methods for "mblogit" and "mclogit" models.

0.8.4.2

• Improved documentation of estimation of baseline-logit models with overdispersion

0.8.4

• A "REML" variant is added to the PQL and MQL estimators for random-effects logit models.
• There is now a simulate() method for objects created by mclogit() or mblogit() (that do not involve random effects)

0.8.2.1

This is a bugfix release, addressing issue #7

0.8.2

• Added support for estimating (over-)dispersion parameters, based on techniques described in Afroz et al (2019)
• getSummary() methods are now explicitly declared in the NAMESPACE file. Package examples now also run on R 4.0.

0.8

• Support for the MQL technique of approxiate inference for random effects multinomial logit models is added.
• The algorithm for the computation of random effects multinomial logit model estimates is more stable, because estimates from the model variant without random effects are not used as starting values. (It appears paradox, but starting values from the no-random effects model variant created numerical instabilities in some instances.)
• The documentation now contains reference to the relevant literature, notably Agresti (2002), Breslow & Clayton (1993), and McFadden (1973).

0.7.2

• Fixes embarrassing bug that prevented estimation of models with more than two levels of random effects.
• Handles numerical difficulties more gracefully by giving users options to deal with them.