Ecologists often rely on observational data to understand causal relationships. Although observational causal inference methodologies exist, model selection based on information criterion (e.g., AIC) remains a common approach used to understand ecological relationships. However, such approaches are meant for predictive inference and is not appropriate for drawing causal conclusions. Here, we highlight the distinction between predictive and causal inference and show how model selection techniques can lead to biased causal estimates. Instead, we encourage ecologists to apply the backdoor criterion, a graphical rule that can be used to determine causal relationships across observational studies.

Research in ecology and evolutionary biology (EEB) plays a key role in understanding and intervening in our current environmental and climate crisis. Although anthropogenic stressors and climate change continue to disproportionately affect Black, Indigenous, and people of colour (BIPOC) individuals, their valuable scientific voices are shockingly underrepresented within EEB. To underscore this problem, we present a case study on EEB PhD graduates in the US (1994-2018), which illustrates that BIPOC scholars are significantly underrepresented in their cohorts. We recommend key steps that the EEB Academy should take to increase representation of BIPOC scholars in EEB, including anti-racism education and practice, increased funding opportunities, integration of diverse cultural perspectives, and a community-minded shift in PhDs. Importantly, this advice is directed at those who wield power in the Academy (e.g., funding agencies, societies, institutions, departments, and faculty), rather than BIPOC scholars already struggling against inequitable frameworks in EEB.