Data Visualization for COVID-19

24/10/2020

Introduction

The COVID-19 Pandemic has become among the worst global pandemics in history due to its implications on both the health and economies of countries around the world.
The devastating nature of the COVID-19 Pandemic can be largely attributed to the interconnectedness in the world today, with ease of movement across the world through air transport.
In order to manage the COVID-19 Pandemic, it is important to understand the ability of a country to use air transport, given that air transport is expensive, and the underlying health factors across a country’s population that may increase spread of COVID-19

Among the various ways that data can be analyzed, is through data visualization.
Data visualization can be defined as an analytic process that is concerned with the presentation of data in the form of tables and charts, as opposed to figures (Martinez, Martinez, & Solka, 2010).
Although data visualizations are often used as complimentary approaches for other analytic processes, they are capable of being stand alone approaches themselves.

The aim of this study is to apply the various techniques under data visualization, and combine this knowledge with the available data on COVID-19 to create a picture of the pandemic itself and its relationship to other factors.
The factors that will be considered in this case are the GDP per capita and prevalence of cardio vascular diseases to relate to, a country’s use of air transport, given that air transport is expensive, and the underlying health factors across a country’s population.

The data on COVID-19 was mined and retrieved from (Our World in Data, 2020).
The data is generally composed of three variable groups; corona-related variables, demographic variables and health-related variables. In total, the data contains 41 variables across these three groups.
The observations are captured for the period from the onset of the pandemic, in January 2020 through to October 2020, resulting in a total of 52010 observations.
The data preparation steps involved both data cleaning and data mutation. Data cleaning refers to a data preparation process that removes observations of attributes that have aspects that are either not needed in the analysis or have the potential to result in misleading findings (Arif & Mujtaba, 2015). Data mutation, on the other hand, is a data preparation method that creates new variables from the existing variables (Shaffer, 2011).

The study presents the data on COVID-19 with an intention of relating the deaths due to COVID-19 to GDP per capita and cardio vascular death rate.
The observation of the trend in new deaths due to COVID-19 showed random spikes in figures with a possible average decreasing trend. The comparison of number of deaths showed North America and Europe lead.
The study also showed more countries in Africa, Asia and Europe have high rates of deaths from the Cardio Vascular diseases while more countries in Asia and Europe have high GDP per capita.

Arif, M., & Mujtaba, G. (2015). A survey: data warehouse architecture. International journal of hybrid information technology, 8(5), 349-356.

Kirk, A. (2016). Data Visualization: A Handbook for Data Driven Design (2nd ed.). Thousand Oaks, CA: Sage Publications, Ltd.

Martinez, W. L., Martinez, A. R., & Solka, J. (2010). Exploratory Data Analysis With MATLAB, 2nd Edition (1 ed.). London: CRC/Chapmann & Hall.

Provost, F., & Fawcett, T. (2013). Data science and its relationship to big data and data-driven decision making. Big Data, 1(1), 51-59.

Shaffer, C. A. (2011). Data Structures and Algorithms Analysis. Mineola: Dover.

Vicenc, T. (2017). Studies in Big Data (1st ed.). Chicago: Springer International Publishing.