JDS Journal of Data Science 1680-743X 1680-743X SOSRUC JULY8 10.6339/JDS.202007_18(3).0018 Research Article Data Visualization and Descriptive Analysis for Understanding Epidemiological Characteristics of COVID-19: A Case Study of a Dataset from January 22, 2020 to March 29, 2020 Charvadeh Yasin Khadem Department of Statistical and Actuarial Sciences, University of Western Ontario, London, Ontario, Canada Yi Grace Y Department of Statistical and Actuarial Sciences, University of Western Ontario, London, Ontario, Canada 2Department of Computer Science, University of Western Ontario, London, Ontario, Canada 18 3 526 535

COVID-19 is a disease caused by the severe acute respiratory syndrome coronavirus 2 (SARSCoV-2) that was reported to spread in people in December 2019. Understanding epidemiological

features of COVID-19 is important for the ongoing global efforts to contain the virus. As a

complement to the available work, in this article we analyze the Kaggle novel coronavirus dataset

of 3397 patients dated from January 22, 2020 to March 29, 2020. We employ semiparametric

and nonparametric survival models as well as text mining and data visualization techniques to

examine the clinical manifestations and epidemiological features of COVID-19. Our analysis

shows that: (i) the median incubation time is about 5 days and older people tend to have a

longer incubation period; (ii) the median time for infected people to recover is about 20 days,

and the recovery time is significantly associated with age but not gender; (iii) the fatality rate

is higher for older infected patients than for younger patients

 incubation time recovery time risk factors survival analysis symptom onset text mining