Skip to main content
Let’s DAG in – How DAGs can help Behavioural Ecology be more transparent

Let’s DAG in – How DAGs can help Behavioural Ecology be more transparent

This is a Preprint and has not been peer reviewed. This is version 2 of this Preprint.

Add a Comment

You must log in to post a comment.


Comments

There are no comments or no comments have been made public for this article.

Downloads

Download Preprint

Authors

Mirjam Borger , Aparajitha Ramesh

Abstract

Directed acyclic graphs (DAGs) are powerful tools for visualizing assumptions/hypothesis and causal inference. Although their use is becoming more widespread across various disciplines, they remain underutilized in behavioural ecology and evolution. Here, we point out why DAGs can serve as highly valuable tools in this field, particularly in the context of observational and field studies, which can feature many variables with complex relationships. Using concrete examples, we show that including DAGs into empirical studies helps clarify and summarise the key underlying assumptions, which are often implicit. With that, DAGs can be used to make researchers aware of bad controls and help them to explicitly think through the relationship between variables and their inclusion in statistical models. In addition, providing DAGs makes the work of reviewers and meta-analysis researchers easier, more rigorous and reliable. Overall, DAGs enhance understanding and transparency, ultimately improving study reproducibility and contributing to greater reliability and replicability across the field. With this paper, we hope to encourage all behavioural ecologists to include DAGs in their papers. 

DOI

https://doi.org/10.32942/X22P7S

Subjects

Life Sciences

Keywords

causal inference, transparent science, Science Communication, bad controls

Dates

Published: 2024-08-28 01:59

Last Updated: 2025-04-15 02:14

Older Versions

License

CC-By Attribution-NonCommercial-NoDerivatives 4.0 International

Additional Metadata

Language:
English

Data and Code Availability Statement:
Not applicable