The COVID-19 pandemic has had different impacts in different regions of the world. Your challenge is to perform a comparative analysis of the pandemic’s economic impacts in urban areas for the USA, Asia, and Europe using the EO Dashboard.
We have developed a Composite Indicator that serves as a statistical tool to assess pandemic preparedness of a region. A large amount of mathematical modeling of the theoretical framework has been done using normalization, imputation, PCA, weighting, and aggregation. 25 original equations formulated by assigning new symbols are prepared for transparency and accountability. The method of building the indicator is generalized for N-dimensional datasets, hence making it more powerful. The results and the final scores of Asia, Europe, and the USA have been visualized using charts. We suggest that Pandemic Preparedness Index (PPI) can cause a revolution in policymaking through statistics.
Melancholy due to the havoc created by the COVID-19 pandemic that forced us to suffer a fate worse than death motivated us to develop this project to highlight the shortcomings of the countries which suffered massive devastation. We chose the ‘A Comparative Analysis’ challenge for the EO Dashboard Hackathon to develop composite indicators using the individual indicators provided in the ‘Earth Observing Dashboard”. Through this challenge, we were able to contribute to the world in overcoming the shortcomings and preparing for the future pandemics that have yet to cause devastation.
To develop this project, the foremost task was to understand the mechanism behind the construction of composite indicators. We went through several documents and websites to learn the essence and principles to construct a composite indicator. After dividing the task among the team members, we began our journey of exploration, learning, and innovation. We learned Data Imputation to give credibility to the available data; Data Normalization to make the data comparable to each other; Physical Component Analysis to obtain a rotated component matrix to calculate the weights of the variables. Finally, we calculated the final scores of the data-specific regions ( in our case: Asia, Europe, and the US) to compare their tumbled socio-economic status due to the COVID-19 pandemic.
Throughout the journey of playing with data, getting meaningful information, and creating a proxy of our own, we required several tools that we had never heard of before. Without a doubt, the EO Dashboard provided us with most data that we used throughout the hackathon. Also, we obtained useful data from the ‘EuroDataCube’ platform. Still, we didn’t get enough data to make our project successful. After inquiring with the team, we finally obtained all the required data through Github and AWS CLI as well. The most useful computer software without which this project would have been impossible to create is SPSS ( a statistics tool developed by IBM). With the help of the python programming language and the statistical tools provided within SPSS, we were able to perform ‘Data Imputation’ and ‘Principal Component Analysis’ to obtain rotated factor loadings which helped us calculate weights. Weighting helped us calculate the ‘Pandemic Preparedness Index(PPI)’ scores to indicate the most and least prepared regions among Asia, Europe, and the US. Ultimately, we created something that maybe one day will prevent some countries from devastation due to the coming challenges.
From choosing a challenge to creating a composite indicator, we stumbled upon several challenges and pondered over their solutions. Extracting data from AWS CLI was the most time-consuming and challenging part. Furthermore, the missing data in the imputed results hindered our way towards the next steps. Understanding the complex Mathematics of ‘Principal Component Analysis’ consumed a lot of our time and energy. Entering the data in SPSS and excel spreadsheets was the most boring task. But we persevered. With the help of the available tools and techniques, with the help of the EO Hackathon expert’s guidance, and with dedication and enthusiasm, we were able to overcome all the challenges and finally create something that will give ‘Pandemic Preparedness Index(PPI)’ scores to the countries of the entire world, help them amend their mistakes and overcome their shortcomings.
In short, we would like to express that this hackathon enabled us to delve deeper into the realm of data mining and analytics. Our labor throughout the Hackathon bore something that we can be proud of that we expect one day will prevent future devastations. Employed with the skills and experiences that we harbored, we are ready to apply our Pandemic Preparedness Index to nations all over the world and help them prepare in advance for the upcoming challenge that mother nature has to offer.
The data provided by the EO Dashboard helped us to accurately demonstrate our ideas through our project to construct a composite indicator to show the preparedness and socio-economic status of the countries during the COVID-19 pandemic. After venturing through the data resources guide, we learned the kinds of data available to us and how to extract them.
As our project required data related to socioeconomic changes, we got data indicating air quality, water quality, and car density in CSV format from the EO Dashboard. Through Jupyter Notebooks in the EuroData, we obtained data indicating other socio-economic changes such as social mobility, quality of life, etc. To get data of specific regions, we used AWS CLI to download .tif and extracted raster images into CSV format using QGIS software.
Extracting data was not the end as our project required us to impute, normalize, manipulate, and analyze the available data. Learning statistical jargon, playing with SPSS ( a statistical tool developed by IBM), delving into the complex world of Principal Component Analysis and Factor Analysis, we succeeded in creating a composite indicator that showcases their weak socio-economic areas.
Finally, we'd say that the data provided by the space agencies helped us perceive the effect of the COVID-19 pandemic on the world and motivated us to create a proxy which we expect to help countries realize their shortcomings and prepare for a better future.
The main approach of our project is to build the framework for the ‘Pandemic Preparedness Index(PPI)’ that allows policymakers and global leaders to understand the preparedness of a geopolitical region during the global pandemic of COVID-19 undertaking the data of change caused by it. We have applied the Earth Observatory Dashboard indicator to form a composite indicator based on three major pillars of social mobility, COVID-19, and climate. The obtained dataset using SPSS can be used in Earth Observatory Dashboard for benchmarking countries of best performance based on the value of major pillars.
The best way to integrate our indicator in the EO Dashboard would be to first integrate the SPSS course ( Since our data was extracted using SPSS) and calculate the PPI for nations throughout the world by applying our methodology. After our indicator is integrated into the EO Dashboard, it would be easier to convey our innovation to the entire world. Every nation can find its won PPI and pinpoint its shortcomings during the COVID-19 pandemic and work to conquer them and prepare for future challenges.
Our solution gives a reliable overall picture of the Covid - 19, economic and climatic situation of different countries and allows for cross-country comparisons which can be implemented on EO Dashboard. Moreover, our indicator highlights the weak socio-economic areas which are devastated due to any unexpected disturbances in the socio-economic cycle allowing the affected countries to perceive and fathom their shortcomings, seek help from the already prepared countries and prepare for the upcoming challenges that nature has to offer.
1) Michela Nardo, Michaela Saisana, Andrea Saltelli, and Stefano Tarantola, Anders Hoffmann, and Enrico Giovannini et.al; (2008); Handbook on Constructing Composite Indicators: Methodology and User Guide; ISBN 978-92-64-04345-9
2) Michela Nardo, Michaela Saisana, Andrea Saltelli & Stefano Tarantola; (2005); Tools for Composite Indicators Building; EUR 21682 EN
3) Mark Skeith & Jerome Gallagher; (August 1, 2019); Composite Indicators: An introduction to their development and use
4) Giuseppe Munda and Michela Nardo; (2005); Constructing Consistent Composite Indicators: The Issue of Weights; EUR 21834EN
5) Michaela Saisana and Stefano Tarantola; (2002); State-of-the-art Report on Current Methodologies and Practices for Composite Indicator Development; EUR 20408 EN
6) El Gibari, S., Gómez, T., & Ruiz, F.; (2018); Building composite indicators using multicriteria methods: a review. Journal of Business Economics; doi:10.1007/s11573-018-0902-z
7) José A. Gómez-Limón, Manuel Arriaza and M. Dolores Guerrero-Baena; (2002); Building a Composite Indicator to Measure Environmental Sustainability Using Alternative Weighting Methods; doi:10.3390/su12114398
Data References:
1) https://eohack- assets.eodashboardhackathon.org/media/documents/D ashboard_Technical_Background_and_Integration_G uide_YnhFQwt_PzXzcvY.pdf
2) https://eohack- assets.eodashboardhackathon.org/media/documents/D ata_Resources_Guide_June_25.pdf
3) https://github.com/CSSEGISandData/COVID-19
4) https://eurodatacube.com/
5) https://eo-dashboard-hackathon-uhbijnokm-nbviewer.hub.eox.at/notebooks/eo-dashboard-hackathon/notebooks/geodb_and_google-mobility-data.ipynb
#economics #CompositeIndicator #Statistics #DataMining #DataAnalysis #Mathematics #SPSS #ComparativeAnalysis #Indicator #COVID-19 #ClimateChange #Society #Economy #Original
This project has been submitted for consideration during the Judging process.