From 680e9bad267fd0a512851dfb101ee9127967e0b9 Mon Sep 17 00:00:00 2001 From: Vincent Arel-Bundock Date: Fri, 15 Sep 2023 15:06:56 -0400 Subject: [PATCH] news + version bump --- DESCRIPTION | 2 +- NEWS.md | 4 ++++ 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/DESCRIPTION b/DESCRIPTION index 2692ed1ad..f9c5fb526 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -1,6 +1,6 @@ Package: marginaleffects Title: Predictions, Comparisons, Slopes, Marginal Means, and Hypothesis Tests -Version: 0.15.0.9001 +Version: 0.15.0.9002 Authors@R: c(person(given = "Vincent", family = "Arel-Bundock", diff --git a/NEWS.md b/NEWS.md index 167b9541a..2625309d7 100644 --- a/NEWS.md +++ b/NEWS.md @@ -9,6 +9,10 @@ Documentation: * New section on "Complex aggregations" in the Hypothesis testing vignette. +Bug fix: + +* Results of the `predictions()` function can be undesirable in version 0.15.0 when (a) `type=NULL`, (b) model is `glm()`, and (c) the `hypothesis` argument is non-numeric. This is because the default `type` was then set to `invlink(link)`, but the backtransformation using link function was applied to the quantity *after* applying the (non-linear) `hypothesis` test (ex: pairwise comparison or contrast). The `hypothesis` funtion should be applied to predictions on the response scale instead. A warning is now issued and the value of `type` is automatically switched to "response" when appropriate. Thanks to @strengejacke for report [#903](https://github.com/vincentarelbundock/marginaleffects/issues/903) + ## 0.15.0 New: