Case09B-Calibrating Clustering Indicators WTVR and Compactness

Chapter 9 Regionalization Methods and Application in Analysis of Cancer Data

The case study in this chapter analyzes variations of breast cancer rates across various constructed regions in Louisiana. Part 1 introduces several one-level regionalization methods such as SCHC, SKATER, AZP , Max-P and REDCAP methods. Part 2 implements various clustering indicators. Part 3 illustrates the implementation of Mixed Level Regionalization (MLR) method, which decomposes areas of large population and merges areas of small population simultaneously to derive regions with comparable population size. The construction of new regions enables us to map reliable cancer rates.
The case study is developed from the research reported in Mu et al. (2015). The data used in this project is provided a zip file LA _ Mixtracts.zip under the folder Louisiana, which includes 1,132 census tracts in Louisiana. Its attribute table includes the following fields:

1. POPU is population, Count02 to Count06 stand for the yearly cancer counts from 2002 to 2006, and Count02 _ 06 is the 5-year sum of cancer counts across census tracts.

2. Fact1, Fact2 and Fact3 are three factor scores consolidated from 11 census variables, labeled “Socioeconomic disadvantages”, “High health care needs”, and “Language barrier” respectively (Wang, Guo, and McLafferty 2012). A higher score of any of the three factors corresponds to a more disadvantaged area. The three factors are used for measuring attribute similarity in the regionalization methods.

The resulting dataset LA _ Result.zip in Step 4 of Section 9.1.2 is also included for user’s convenience.

Case Study 9 Part 1: One-Level Regionalization
Case Study 9 Part 2: Calibrating Clustering Indicators WTVR and Compactness
Case Study 9 Part 3: Mixed-Level Regionalization (MLR)

Computational Methods and GIS Applications in Social Science - KNIME Lab Manual
Lingbo Liu, Fahui Wang

External resources

• Github for Workbook Issue Report
• Github for Geospatial Analytics