Add support for "kenward" option

[strengejacke]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @strengejacke, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request streamlines the handling of Kenward-Roger approximations within the parameters R package. By refactoring the core Kenward-Roger logic to utilize the insight package, the codebase becomes more maintainable and consistent. A key improvement is the automatic enforcement of Restricted Maximum Likelihood (REML) fitting for models when Kenward-Roger methods are requested, preventing common pitfalls. Furthermore, this change extends robust statistical inference capabilities to glmmTMB models, allowing users to apply Kenward-Roger adjustments for more accurate confidence intervals and p-values in a wider range of mixed-effects models.

Highlights

• Kenward-Roger Refactoring: The complex internal implementation for Kenward-Roger degrees of freedom and variance-covariance matrix adjustment has been largely replaced by a single call to the insight::get_df function, significantly simplifying the codebase.
• REML Enforcement: Functions like ci_kenward, p_value_kenward, and se_kenward now explicitly check if a model was fitted using Restricted Maximum Likelihood (REML) and will re-fit the model with REML if it wasn't, ensuring correctness for Kenward-Roger approximations.
• glmmTMB Support: The "kenward" and "kr" methods for confidence intervals and standard errors are now officially supported and validated within model_parameters.glmmTMB, ci.glmmTMB, and standard_error.glmmTMB functions, extending functionality to glmmTMB models.
• Package Version Update: The package version has been incremented from 0.28.2.7 to 0.28.2.8.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request adds support for the "kenward" option for degrees of freedom approximation, particularly for glmmTMB models. A significant and beneficial change is the refactoring of the Kenward-Roger implementation, moving the complex logic to the insight package, which greatly simplifies this package's codebase. The changes are generally well-executed. However, I've identified a critical bug in se_kenward() where an undefined variable is used, which will cause an error. I've also pointed out a minor style issue that impacts code readability. Addressing these points will solidify the improvements made in this PR.

[strengejacke]

@gemini-code-assist review

[Copilot]

Pull Request Overview

This PR adds support for the "kenward" (Kenward-Roger) approximation method as a ci_method option for mixed models, particularly extending support to glmmTMB models. The implementation includes comprehensive refactoring of existing Kenward-Roger functions to use S3 methods and delegation to the insight package for more efficient calculations.

• Refactored Kenward-Roger functions to use S3 method dispatch and delegate calculations to insight::get_df() and insight::get_varcov()
• Added full support for Kenward-Roger and Satterthwaite methods in glmmTMB models
• Updated test suite with extensive coverage for the new functionality across different model types

Reviewed Changes

Copilot reviewed 16 out of 17 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
tests/testthat/test-model_parameters_df_method.R	Comprehensive test updates adding glmmTMB model testing and validating Kenward-Roger method consistency
R/standard_error_kenward.R	Converted to S3 methods with glmmTMB support using insight::get_varcov()
R/p_value_kenward.R	Simplified implementation removing model-specific methods, added REML refitting logic
R/dof_kenward.R	Streamlined to delegate to insight::get_df() instead of custom implementation
R/dof_satterthwaite.R	Simplified to use insight::get_df() delegation
R/ci_kenward.R	Added S3 methods with specific glmmTMB support and component handling
R/ci_satterthwaite.R	Added conditional component support for glmmTMB models
R/methods_glmmTMB.R	Enhanced with Kenward-Roger and Satterthwaite method support in parameter extraction
man/p_value_kenward.Rd	Updated function signatures to include ellipsis parameters
inst/WORDLIST	Added lcmm to spelling dictionary
NEWS.md	Documentation of new glmmTMB support for advanced CI methods
NAMESPACE	Updated exports for new S3 methods
DESCRIPTION	Version bump to 0.28.2.8
.github/SUPPORT.md	Simplified reprex documentation reference
.github/CONTRIBUTING.md	Removed specific tidyverse reprex link
R/ci_generic.R	Added formatting comments and parameter restructuring

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[gemini-code-assist]

Code Review

This pull request is a significant and well-executed refactoring. It adds support for Kenward-Roger and Satterthwaite approximations for glmmTMB models, which is a valuable feature. The approach of moving the complex calculations to the insight package and creating generic functions in parameters greatly improves the code's structure and maintainability. The changes are consistent across different functions, and the addition of comprehensive tests ensures the new functionality is working correctly and doesn't introduce regressions. I've found one minor issue regarding some leftover dead code, which I've commented on. Overall, this is an excellent contribution.