Week 9: Spatial Analysis
Joplin C -
Hey there!
I can’t believe that we are almost finished! This past week, I worked on the spatial analysis of all the maps I’ve created previously!
I performed a Local Bivariate Spatial Analysis, which essentially determines whether there is a significant relationship between two variables per data group (zip code). As I suspected earlier, some of the maps that I made have varying levels of correlation. According to the analysis, the variables with the greatest correlation with heat death rates are poverty rates, tenure status, healthcare coverage, unemployment rate, exposed commutes, and median household income.
There were other variables that I included in the analysis that had a minimal relationship with heat deaths, such as commute time and daytime commutes. This makes sense, however, as higher commute times seemed to be more correlated with living on the outskirts of the city, away from the urban heat island effect. Daytime commutes also make sense, as the majority of workers commute via car, which is less exposed to heat.
Overall, I now have a definite idea of which socioeconomic factors have the greatest correlation with heat-related illness, which will be crucial to highlight in my final presentation!
Now that all of the data preparation is finished, I am looking to begin working on my final presentation! I am currently thinking of a StoryMap-dashboard as my final product, and I look to further incorporate my maps into my presentation as well! Stay tuned for more and I will see you all next time!
Joplin Chambers