At this point Bhramar Mukherjee (University of Michigan) is no stranger to research on better understanding the COVID-19 virus. She showed to us how she used the statistical power to help inform lockdown policies in India. Her comments during this session involved a review and discussion of pre-lockdown forecasting, post-lockdown analysis and daily projection updates specifically focusing on what has and is happening in India. In addition, it is admirable that as a core faculty member associated with the Michigan Institute of Data Science (MIDAS), besides embracing her administrative responsibility to ensure diligence in the research her group undertakes, she also sees herself embracing another role. By leveraging the efforts of a host of mostly international graduate students not only was she able to scale up research efforts, she also saw how this workserved to offset the anxiety the pandemic caused students far from home by allowing them to play a more meaningful and direct role in helping from a distance. (see Event page)
Bhramar’s session is really a story of learning - learning about infectious disease modeling and finding ways to impact our community and even the world. She starts with intitial modeling, how the number of cases dramatically increased, the initial predictions that were made, and the lessons learned not only about these prediction intervals but also how these predictions are perceived by both policy makers and the Media.
She then walked through the details of a first, simple SIR forecasting model and exactly how this model was then extended and enhanced to fit the requirements of the research problem as it presented itself. Once implemented she was able to demonstrate the general ideas behind what these models allowed her group to estimate and then through this type of analysis the projections they were able to obtain. Extensive discussion of these results followed, emphasizing what was learned as they moved forward, then using what they learned to implement new approaches, produce new model projects and learn from this, and so forth. Throughout this circular learning process she emphasized the importance “rigorous science but done in a nimble manner!”
Besides her work with data, Bhramar also discussed the challenges of working in the population found in India but she also took time to emphasize the changes that have taken place to mitigate the virus. For instance, there is much evidence of the scaling up of infrastructure concerning health care capacity. Services such as the number of tests per day, ICU beds, and COVID care centers all increased dramatically, and the price per test dropped. She demonstrated how research is not only about the data, models and analysis, but how in this case it is also about the impact it has on human lives as well.
“The public has a serious role in public health. We need to manage risk in our daily lives.”
Bhramar Mukheljee (University of Michigan)
Moderator Lili Zhao (University of Michigan) fielded questions from an attentive audience and asked Bhramar a few questions of her own. Some of these questions included: “What are some common and distinct features of modeling data from India and the US.?”, “How was the undercounting in the COVID-19 data in India adjusted in your estimation and forecasting?” and “What can we learn from the experience of the implementation and the messaging of public health intervention from India?” The responses to these questions and the discussion it raised can be reviewed in the recording of the event below.
Want to learn more? Mark your calendar for every 1st and 3rd Thursday from noon to 1 pm ET. (See the NISS website for event details and to register for these sessions!)
Below, please find a recording of this session along with a link to the slides that the speaker used. The slides not only provide you with the key points that were offered but also include links to additional resources that should not be ignored!
Recording of the Session
Slides used by the Speaker
Bhramar Mukherjee, (University of Michigan)
Moderator: Lili Zhao, (University of Michigan)
About this Webinar Series
The COPSS-NISS COVID-19 Data Science webinar series is co-organized by the Committee of the Presidents of Statistical Societies (COPSS) and its five charter member societies (ASA, ENAR, IMS, SSC, and WNAR), as well as NISS. This bi-weekly seminar features the latest research that is positioned on the cusp of new understanding and analysis of COVID-19 pandemic data, and promotes data-driven research and decision making to combat COVID-19. Find out more about this series and view all the previous sessions on the Webinar Series page.