In order to get my hands dirty with R, I did a simple univariate exploratory analysis of the HIV prevalence dataset from Gapminder. The analysis drills down on the countries with the highest and lowest prevalence and seeks to find explanations of why such a gap exists between them. I postulate some exogenous factors that might be corrupting the data and seek to contextualize the information using subject-specific sources.
The exercise was useful in learning the basics of R and data analysis, but I think more datasets would be needed to add more context and value to the analysis. Marking the countries based on their region might also have been useful to get a better picture of inter and intra-regional trends. In future projects, I’d like to make use of colors, facet_wrap, and other tools for multi-variate analysis.
Link to the analysis here
Link to github repository here