Summary

In this chapter, you learned how to construct multiple hypothesis tests. Each hypothesis test was conducted with the null hypothesis (H0) as CSR. The alternative hypothesis (Ha) in each case was that data exhibited a non-random, spatially significant relationship.

For data where the attribute features were important, you conducted tests of global spatial autocorrelation, leveraging Moran’s I and Geary’s C. You also learned how to identify known spatial outliers and hot and cold spots through the use of LISAs.

At the end of the chapter, you learned how to conduct hypothesis testing on point data where the distribution of the points themselves was of interest. The tests you conducted here were based on Ripley’s alphabet functions, which looked at the nearest neighbor distance distributions and full-distance distributions.

Now that you’ve thoroughly explored this data, it can be leveraged in future exercises. We hope you’re excited to...