Search

29 Apr 2024: Small Data, Big Time—A retrospect of the first weeks of COVID-19. Qingyuan Zhao. [To be read before The Royal Statistical Society at the Society’s 2021 annual conference held inManchester on Wednesday, September 8th, 2021, the President, Professor Sylvia Richardson, in theChair]. Abstract. This article reviews some early investigations and research studies in the first weeks of the coron-avirus disease 2019 (COVID-19) pandemic from a statistician’s perspective. These investigations werebased on very small datasets but were momentous in the initial global reactions to the pandemic. Thearticle discusses the initial evidence of high infectiousness of COVID-19 and why that conclusion wasnot reached faster than in reality. Further reanalyses of some published COVID-19 studies show thatthe epidemic growth was dramatically underestimated by compartmental models, and the lack of fitcould have been clearly identified by simple data visualization. Finally, some lessons for statisticiansare discussed.Keywords: Infectious disease modeling; Selection bias; COVID-19; Model diagnostics. 1 Introduction. Starting from a regional disease outbreak in Wuhan, China, the coronavirus disease 2019 (COVID-19)rapidly grew into a once-in-a-lifetime