This is an online COVID-19 pre-publication manuscript which has been submitted to WPSAR. Pre-publication manuscripts are preliminary reports and have not been peer-reviewed. They should not be regarded as conclusive, guide clinical practice/health-related behavior, or be reported in news media as established information. Statistical investigation of COVID-19 spread: a regression analysis Macole Sabat 1 , Amany Fayssal Chahine 2,3 , Mira Sabat 4,a 1 Mechanical Engineering Department, Faculty of Engineering, University of Balamand, Lebanon, macole.m.sabat@balamand.edu.lb 2 School of Veterinary medicine, Faculty of health and medical sciences, University of Surrey, United Kingdom 3 Department of Biology, Faculty of Arts and Sciences, University of Balamand, Lebanon, a.chahine@surrey.ac.uk 4 Department of Mathematics, Faculty of Arts and Sciences, University of Balamand, Al Kurah, Lebanon, mira.sabat@balamand.edu.lb a Corresponding author Abstract This paper presents a statistical investigation of the COVID-19 spread in 31 countries from 31 December 2019 to 26 March 2020. It shows that the total number of infected persons follows the same trend in almost all countries using a regression analysis and they fit a third-degree polynomial. The obtained profiles are validated with the number of infections in 26 and 27 March with an estimate of the percentage error. These theoretical profiles can be used to estimate the number of infections in the sharp increase phase. In addition, a grouping of the different countries was put in place. This is done based on an estimate of the Poisson parameter and on the sign of the leading coefficient of the fitted polynomial. The obtained results may help the countries in the early phases to compare to their similar counterparts and take the necessary measures to limit the virus spread.