Add support for vcovHC for package glmmTMB

[strengejacke]

Fixes #1151

[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 significantly enhances the parameters package's capabilities for glmmTMB models by integrating support for robust variance-covariance matrix estimation. The changes allow users to specify various types of robust standard errors, such as heteroskedasticity-consistent (vcovHC), cluster-robust, and bootstrap-based methods. This improves the reliability of statistical inference by providing more accurate standard errors and p-values, particularly in situations where model assumptions might not hold. The update includes modifications to core parameter and standard error extraction functions, along with comprehensive documentation for the new features.

Highlights

• Enhanced Parameter Estimation with Robust Variance-Covariance: The core functionality of the model_parameters.glmmTMB function has been extended to accept vcov and vcov_args parameters. This allows users to specify custom or robust variance-covariance matrices for parameter estimation, enhancing the flexibility and robustness of statistical inference.
• Robust P-Value and Standard Error Calculation: New methods have been introduced for p_value.glmmTMB and standard_error.glmmTMB that leverage the new vcov and vcov_args parameters. This enables the calculation of robust p-values and standard errors, which are crucial for reliable inference, especially when assumptions about error distributions are violated.
• Introduction of Internal Robust Standard Error Helper: An internal helper function, .se_robust_glmmTMB, has been added to encapsulate the logic for computing robust standard errors. This promotes code reusability and maintainability for robust estimation across different functions.
• Dependency and Version Updates: The DESCRIPTION file has been updated to reflect a new package version and increased minimum version requirements for key dependencies like insight, glmmTMB, and tinytable, ensuring compatibility and access to necessary features for the new functionality.
• Updated Documentation for Robust Estimation: Comprehensive documentation has been added for the vcov and vcov_args parameters in the model_parameters.glmmTMB help file. This provides users with clear guidance on how to utilize the new robust variance-covariance options, including examples of supported types from external packages like sandwich and clubSandwich.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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 robust variance-covariance matrix estimation (e.g., vcovHC) for glmmTMB models. The changes correctly add vcov and vcov_args parameters to model_parameters.glmmTMB and standard_error.glmmTMB, and remove the previous restrictions. However, the newly introduced p_value.glmmTMB function has a critical issue where it's implemented to return standard errors instead of p-values, and it also has a bug that would cause a runtime error. I've provided a detailed comment with a corrected implementation for this function. The other changes, including documentation updates and dependency bumps, look good.