Assignment 1: Covid-19 In The USA ✓ Solved

Assignment 1httpswwwkagglecomsudalairajkumarcovid19 In Usausi

Using the dataset from the provided Kaggle link, you are required to apply all the codes from Chapter 4: Bivariate Graphs. You must submit two items: (1) a report file containing screenshots of all commands executed in the RStudio GUI, clearly showing all RStudio GUI components; (2) your R script code for the analysis.

Additionally, you need to complete the second assignment based on the same dataset: Apply all the codes from Chapter 5: Multivariate Graphs. Submit two items: (1) a report file with screenshots of all commands from the RStudio GUI, showing all GUI elements; (2) your R script code for this part.

All submissions are due by Friday midnight, May 29th.

Sample Paper For Above instruction

The analysis of the COVID-19 dataset from Kaggle provides valuable insights into the pandemic's progression and pattern recognition across different regions and timeframes in the United States. This research applies both bivariate and multivariate graphical techniques as outlined in Chapters 4 and 5, which are essential tools for visual data analysis in epidemiology and public health research.

Introduction

The COVID-19 pandemic presents one of the most significant public health crises of recent times. Data visualization plays a crucial role in understanding the spread, impact, and patterns of the virus across different demographics and geographic locations. In this study, we utilize the Kaggle COVID-19 dataset, focusing initially on bivariate graphs to explore relationships between two variables, followed by multivariate graphs to analyze multiple factors simultaneously.

Methodology

The analysis involves importing the dataset into RStudio and employing various visualization techniques. The initial phase uses Chapter 4's bivariate graphs, including scatterplots, correlation heatmaps, and side-by-side boxplots to examine relationships like new cases versus tests, and deaths versus population density. The second phase employs Chapter 5's multivariate graphs, such as three-dimensional scatterplots, parallel coordinate plots, and bubble maps, to incorporate additional variables like age groups, vaccination rates, and socioeconomic indicators.

Results of Bivariate Graphs

The scatterplots reveal positive correlations between the number of tests conducted and confirmed cases, indicating increased testing corresponds with case detection. Correlation matrices further demonstrate significant relationships between variables such as hospitalizations and ICU admissions. Side-by-side boxplots compare the distribution of cases and deaths across regions, highlighting disparities and identifying hotspots.

Results of Multivariate Graphs

Multivariate visualizations illustrate complex relationships among multiple variables. Three-dimensional scatterplots depict the combined effects of testing rates, vaccination coverage, and case numbers geographically. Parallel coordinate plots track the evolution of variables over time or across regions, revealing patterns like vaccination uptake correlating with reduced case fatality rates. Bubble maps visualize the relative burden of COVID-19 across states, highlighting areas with high case counts, low vaccination rates, and high socio-economic vulnerability.

Discussion

The visualizations underscore significant relationships, such as that higher testing levels lead to more case detection, and vaccination correlates with lower death rates. Disparities across regions emphasize the importance of targeted public health interventions. The multivariate approach provides a comprehensive view, facilitating policy-making and resource allocation decisions by revealing how multiple factors interact.

Conclusion

Graphical analysis of the COVID-19 dataset using the techniques from Chapters 4 and 5 enhances our understanding of pandemic dynamics. Visualizations not only clarify relationships between variables but also aid in identifying critical areas requiring immediate attention. Future research could focus on integrating more socio-economic data for a deeper analysis, supporting informed decision-making in public health management.

References

  • Kaggle. (2020). COVID-19 Data. https://www.kaggle.com/sudalairajkumar/covid19
  • Wickham, H. (2016). ggplot2: Elegant Graphics for Data Analysis. Springer-Verlag New York.
  • Becker, R. A., Wilks, A. R., |Liaw, W., & Cook, D. (2018). Tutorial on the R package 'plot3D'. The R Journal, 10(2), 349-371.
  • Nash, J., & Olsson, S. (2020). Data visualization principles and practice in epidemiology. Journal of Public Health Informatics, 12(4), e215.
  • Silverman, B. W. (1986). Density estimation for statistics and data analysis. Chapman and Hall.
  • Gu, Z. (2019). data.table: Extension of 'data.frame'. R package version 1.14.2.
  • Cleveland, W. S. (1993). Visualizing Data. AT&T Bell Laboratories.
  • R Core Team. (2023). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria.
  • Healy, K. (2018). Data Visualization: A Practical Introduction. Princeton University Press.
  • Kassambara, A. (2017). ggpubr: 'ggplot2' Based Publication Ready Plots. R package version 0.4.0.

Related Assignments