Answers are grounded in this paper and cite their sources.
Media reporting and public discourse in the spring of 2020 has been dominated by the discussion of statistics relating to the COVID-19 outbreak and how to intepret them. Reasoning about these numbers has inspired fear as well as hope in communities worldwide. This environment provides a lens, and a rare scale, for data scientists to investigate how complex statistical topics are communicated to, understood by, and acted upon by diverse audiences. In particular, this crisis has put a premium on âdistributional thinking,â a mindset for reasoning about variation that is front and center in the response to the coronavirus as well as broadly relevant to organizations. This kind of thinking is already widespread among data scientists, but the challenge we face is to instill it across our organizations to equip them to tackle complex problems whose response should be informed by data and evidence. Fortunately, ours is not the first domain to encounter this challenge. I suggest learning from the example of modern social justice movements, who have evolved strategies to generate widespread appreciation of issues with distributional considerations, like the disparate impacts of environmental pollution and inequities in policing. I point to movement-building techniques like participatory research and shared leadership for lessons on how to grow the capacity for distributional thinking within companies, NGOs, agencies, and other organizations.
No takes yet. Share an insight, caveat, or question.
Nathan Sanders (2020) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: