Regression Models for Predictions of COVID-19 New Cases and New Deaths Based on May/June Data in Ethiopia

Abstract

BACKGROUND: On 15 th of June 2020, Ethiopia had 3,521 COVID-19 total cases, 60 total deaths (1.7%), 620 total recoveries (17.6%), and 176 new cases. And, only 1,629 total tests were done per 1,000,000 populations. This study aimed to predict COVID-19 new cases and new deaths based on May/June data in Ethiopia using regression models. METHODS: In this study, correlation coefficient analysis and regression models were used for COVID-19 new cases and new deaths data analysis based on the available data from 12 th May to 10 th June 2020 in Ethiopia. RESULTS: Both COVID-19 new cases and new deaths have correlated significantly with different COVID-19 related variables. In models comparison, the simple linear regression model was fitted better than quadratic and cubic regression models for both new cases and new deaths data. In the multiple linear regression model, new cases were predicted significantly by the number of days, daily laboratory tests, and Addis Ababa city new cases. And also, new deaths were predicted significantly by the number of days and new recoveries in the model.CONCLUSIONS: COVID-19 new case was predicted significantly by the number of days, daily laboratory tests and Addis Ababa city cases, and new deaths also predicted significantly by the number of days and new recoveries. The researcher recommended that government of Ethiopia, ministry of health, and regional governments should give more awareness and protections for societies, and they should open more laboratory testing centers. The researcher also recommended that time series models will be included for furthers.