Valerie Nirala, ASA Editor and Content Strategist

In January—when COVID-19 sprang up in China and the world seemingly began to transform daily—statisticians, biostatisticians, data scientists, and epidemiologists went to work turning data into information people could use. Following are some of the ASA members who forged ahead during the crisis and provided direction based on sound statistical practice.

Bhramar Mukherjee of the University of Michigan is part of the COV-IND-19 Study Group, an interdisciplinary group of scholars and data scientists who use data and modeling to generate timely reports and recommendations about COVID-19 in India. The group published an article, titled “Predictions and Role of Interventions for COVID-19 Outbreak in India,” on March 21, four days before India Prime Minister Narendra Modi told everyone they could not leave their homes for three weeks. The article summarizes the group’s technical report and outlines the approach taken to answer the following three questions:

• What can India expect in the next few months?
• How will this affect the general public of India?
• How can the government and people of India prepare for this crisis?

From their predictive model, the group concluded it was “appropriate to adopt draconian measures” and act before the growth of COVID-19 infections in India started to accelerate. The media began quoting the group’s work shortly after the article was published, making it a pivotal piece in guiding the decision to shut down India. Mukherjee also appeared on Indian national television, and the group’s article showed up in such media outlets as the Economic Times, Reuters, Aljazeera, and Business Insider.

Also part of the COV-IND-19 Study Group are ASA members Debashree Ray of The Johns Hopkins University and Rupam Bhattacharyya, Lili Wang, Peter Song, Mousumi Banerjee and Veera Baladandayuthapani of the University of Michigan.

John Ioannidis of Stanford University also made headlines, appearing on CNN opposite Marc Lipsitch, a professor of epidemiology at Harvard, after publishing “A Fiasco in the Making? As the Coronavirus Pandemic Takes Hold, We Are Making Decisions Without Reliable Data” on STAT. His article summarized his technical report, which maintained better data was needed to direct decisions about how to respond to COVID-19 and sparked abundant discussion among both statisticians and nonstatisticians.

Bin Yu of the University of California, Berkeley developed models with her team made up of students and postdocs to connect hospitals with supplies. Working with nonprofit organization Response4Life, Yu’s team collected information from federal, state, and local health agencies, as well as media reports, about shortages to craft data sets. The team then developed algorithms that Response4Life plans to use to build a platform that will connect suppliers and hospitals.

Susan Ellenberg of the University of Pennsylvania Perelman School of Medicine co-wrote a New York Times op-ed, titled “The Coronavirus Is Here to Stay, So What Happens Next?” This piece explained why Americans should expect a roller coaster rather than a curve when it comes to the coronavirus. Referring to the 1918 influenza pandemic and 2003 SARS outbreak, the authors explain how the virus will likely come in waves as social distancing does its job. As more people distance themselves from others, fewer will develop immunity (if, in fact, you can develop immunity), so there will be subsequent rounds of infection with the need to practice social distancing. The authors do point to the upside, saying each resurgence of the virus will come more slowly and each round of social distancing will last for less time.

Xihong Lin of the Harvard T.H. Chan School of Public Health was featured in a webinar summarizing her research outlined in “Evolving Epidemiology and Impact of Non-Pharmaceutical Interventions on the Outbreak of Coronavirus Disease 2019 in Wuhan, China.” She and her coauthors analyzed 25,000+ lab-confirmed COVID-19 cases in Wuhan, describing the epidemiological features of the virus outbreak and evaluating the impact of nonpharmaceutical interventions. The authors concluded extensive countermeasures controlled the COVID-19 outbreak and particular measures are needed to protect healthcare workers, the elderly, and children.

Christopher Bilder who studies group—or pooled—testing and wrote “Group Testing for Identification” for Wiley StatsRef: Statistics Reference Online, has been explaining to the Twitterverse how this technique can be used to test for COVID-19 using less time and fewer resources.

A new book by Ron Fricker of Virginia Tech and Steve Rigdon of Saint Louis University, titled Monitoring the Health of Populations by Tracking Disease Outbreaks: Saving Humanity from the Next Plague, focuses on tracking and monitoring disease outbreaks, including COVID-19. “We were motivated to write the book because the work of public health officials often critically depends on the use of statistical methods to help discern whether an outbreak may be occurring and, if there is sufficient evidence of an outbreak, then to locate and track it,” said Fricker. “With the recent outbreaks of diseases such as swine and bird flu, Ebola, and COVID-19, the role that epidemiologists and biostatisticians play is more important than ever.”

Last but not least, Elizabeth Halloran of the University of Washington and Fred Hutchinson Cancer Center was a source for a New York Times piece, titled “How the Virus Got Out.” This is an interactive visualization showing why stopping travel from China did not stop COVID-19 from spreading. It illustrates exponential growth and how not taking immediate measures allowed the virus to spread.

If you are contributing to the COVID-19 dialog by providing sound data and statistical practices or know of other ASA members who are, email your story to Amstat News Managing Editor Megan Murphy.

A Teachable Moment

Sara Brown, Patrick Hopfensperger, and Henry Kranendonk—authors of Focus on Statistics: Investigations for the Integration of Statistics into Grades 9–12 Mathematics Classrooms—have made available for free Investigation 12: Chances of Getting the Flu?

This investigation develops a probability distribution through the design and use of a simulation involving the spread of flu in an apartment building. It follows the four components of statistical problem-solving put forth in the Guidelines for Assessment and Instruction in Statistics Education (GAISE) Report: formulate a statistical question; design and implement a plan to collect data; analyze the data by measures and graphs; and interpret the results in the context of the original question.

Teachers can download the free investigation on the Statistics Teacher website.