Studio 07 Global Spatial Autocorrelation

Author

Sergio Rey

Instructions

Teams
DUE: Wednesday, October 16, 2024 3:30pm

The team leader will submit a pdf version of the notebook showing all the work to answer the questions.

The first cell of the notebook should have a list of the team members (first and last names) with the team leader in bold. (Hint: Markdown cell).

Input Files

In this studio you will be analyzing the spatial patterns of homicide rates in the southern US Counties, from the South built-in dataset from libpysal.

Join Count Analysis

For each decade that the homicide rate is recorded complete the following:

  1. Create a binary variable reporting high and low county homicide rates using the median rate as the threshold.
  2. Construct a queen contiguity matrix for the counties.
  3. Describe the patterns you see across the decades.
  4. Create a binary map of the spatial distribution for each decade.
  5. Carry out a join counts analysis on the binary variable using the queen contiguity matrix for each decade.
  6. Create a time series plot of the number of BB joins for each decade.
  7. Provide a narrative interpretation of your findings. Specify the null hypothesis for each decade, and state your decision whether to reject or fail to reject the null hypothesis.

Moran’s I Analysis

For each decade that the homicide rate is recorded complete the following:

  1. Create a choropleth map of the spatial distribution of the county homicide rates for each decade.
  2. Describe the patterns you see across the decades.
  3. Carry out a Moran’s I analysis on the original homicide variable using the queen contiguity matrix for each decade.
  4. Create a time series plot of the value of the Moran’s I statistic.
  5. Provide a narrative interpretation of your findings. Specify the null hypothesis for each decade, and state your decision whether to reject or fail to reject the null hypothesis in each period.