Geography and Statistical Relationships
What this module is about
Two very different but related skills: putting data on a map responsibly, and testing whether one variable is actually related to another instead of eyeballing a chart and guessing.
What you'll achieve
You'll map Synthetic_Latitude/Synthetic_Longitude, then test whether Overall_Satisfaction is related to Wait_Time_Minutes, Food_Quality_Rating, and Staff_Respect_Rating.
Exercises
- Map the synthetic coordinates (
Synthetic_Latitude,Synthetic_Longitude) and explain, in writing, why these points should never be treated as real addresses. - Test whether
Overall_Satisfactionis related toWait_Time_Minutes,Food_Quality_Rating, andStaff_Respect_Rating.
Why it matters
Synthetic coordinates are randomized within a real area to make a map look plausible — treating one as a real household's location would be both wrong and a privacy problem if the data ever were real. Exercise 10 is the first exercise that asks you to test a relationship rather than just describe one; correlation or a simple crosstab is enough, you don't need a formal statistical background.
Suggested tools
A mapping tool (Excel 3D Maps, Google Sheets geo chart, or a quick plot with matplotlib/plotly); a correlation matrix or grouped averages for exercise 10.