Changes in version 0.4.2                        

  - added an equatiomatic::extract_eq() method for "nestedLogit" objects
  - added a vignette ("latex-equations") illustrating use of LaTeX
    equations in Rmarkdown / Quarto documents for these models and
    various options available.
  - fixed subtle LaTeX bug in extract_eq() when dichotomy names contain
    "_"
  - added a submodel= arg to avoid $submodel indexing
  - Fixed DOIs in RSQ.R now that CRAN is pickier about their format
  - Fixed documentation nits from Roxygen 8.0.0

                        Changes in version 0.4.1                        

  - Added RSQ() function to compute pseudo-R² measures (McFadden,
    Cox-Snell, Nagelkerke, and others) for each dichotomy sub-model and
    for the combined polytomous model
  - Added examples of RSQ() in the nestedLogit and other-examples
    vignettes
  - Added methods RSQ.multinom() and RSQ.polr()

                 Changes in version 0.4.0 (2026-03-06)                  

This is a major release of the package adding considerable functionality
for plotting and other features

  - add gators data, food choice of alligators from Agresti
  - added a vignette illustrating use of the ggeffects package for
    nestedLogit models
  - added an article showing use of the easystats packages for
    nestedLogit models [not yet a vignette, because work on this is
    continuing]
  - re-factored predict.nestedLogit() and related to its own file for
    improved documentation
  - added ability for direct labels in plot.nested-ci.R
  - Better description of nested logit and other models in README
  - changed default colors for plot.nestedLogit() to use
    scales::hue_pal() for consistency with ggplot
  - added scale argument to plot.nestedLogit() to allow plotting on the
    logit (log-odds) scale (scale = "logit") in addition to the default
    probability scale (scale = "prob")
  - added as.tree() method for ASCII printing of the tree of nested
    dichotomies
  - Added vignette: "Other Examples of Nested Logit Models"
  - In the GSS data, "l.t.highschool" changed to "<highschool"
  - Fixed problem with lty not passed to matplot() in plot.nestedLogit()
  - In plot.nestedLogit(), added label.col argument (defaulting to the
    value of col in the call), to control the color of the curve label
  - Add example of plotting predictions for dichotomies to ggeffects
    vignette
  - Fixed problem in ggeffects vignette with predict_response() for
    nestedLogit models; see ggeffects issue #671
  - Fixed problem in other-examples vignette traced to tibble not
    handled well in plot.nestedLogit
  - Added rhub::rhub_check() workflow.

                 Changes in version 0.3.4 (2026-02-01)                  

This is a minor release, improving documentation

  - add link to pkgdown documentation in DESCRIPTION
  - edit description of nested dichotomies in README to include examples
    and relations with other models

                        Changes in version 0.3.3                        

  - Fixed documentation error in GSS.R
  - createDichotomies methods now explicitly internal

                 Changes in version 0.3.2 (2023-06-22)                  

  - new Effect method for "nestedLogit" objects to create effect
    displays.
  - add Effect example to vignette

                        Changes in version 0.3.1                        

  - correct buglet in as.data.frame method when newdata has one column
  - predict.nestedLogit() now includes the newdata data frame as an
    additional component (.data) in its result. Consequently, the
    newdata argument is no longer required in the as.data.frame method.

                 Changes in version 0.3.0 (2023-05-30)                  

This is a major enhancement to the package, adding computations of
standard errors and confidence intervals to predicted probabilities and
logits.

Enhancements

  - The predict() method now computes standard errors for probabilities
    and logits using the delta method. These can be obtained for either
    the response probabilities (and equivalent logits) or for the
    predicted log odds of the individual dichotomies.
  - A confint() method for the result of predict() generates the
    corresponding confidence intervals.
  - as.data.frame() methods for predicted values, either for the nested
    logit model or for the separate dichotomies converts these to a data
    frame in long format, handy for using ggplot().
  - Added a confint() method for predicted probabilities and logits
  - The plot() method for "nestedLogit" objects now plots confidence
    intervals for predicted probabilities.
  - A new vignette, "standard-errors", describes the mathematics behind
    the standard error calculations.
  - An old vignette on plotting methods was completely re-written using
    the new predict() methods and focusing exclusively on `ggplot2().

Other

  - Added an example of lobstr::tree() to print nested lists
  - Now use fig.show="hold" to keep par(op) with the code.

                 Changes in version 0.2.1 (2023-05-15)                  

  - Reset all par() and options() calls so as to not alter user's
    workspace.
  - now document all return values.
  - added a reference to DESCRIPTION. It is a book, so no doi:, url,
    etc.
  - fixed one URL that win-builder (spuriously) complains about.

                        Changes in version 0.2.0                        

  - Now allow dichotomies to be specified by a nested (recursive) of
    binary splits of the categories [suggestion of Achim Zeileis]
  - The model object is now of class "nestedLogit" for uniformity.
  - A basic plot() method now operational
  - Added a linearHypothesis() method to give Wald tests for hypotheses
    about coefficients or their linear combinations.
  - Expanded vignette to illustrate some other methods.
  - Added a models() generic and method to extract separate models from
    the "nestedLogit" object
  - Added a logLike() method, and through it, gets AIC() and BIC()
  - Reorganized documentation to separate nested hypothesis methods.

                        Changes in version 0.1.0                        

  - Initial version
  - Added a NEWS.md file to track changes to the package.