Regionalization Methods and Application in Analysis of Cancer Data

Rates of rare events (e.g., cancer, AIDS, homicide) are often subject to the small population (numbers) problem, where the denominators are small or vary a great deal. The problem can lead to unreliable rate estimates, sensitivity to missing data and other data errors, and data suppression in sparse...

Full description

Saved in:
Bibliographic Details
Published inComputational Methods and GIS Applications in Social Science - Lab Manual pp. 180 - 195
Main Authors Liu, Lingbo, Wang, Fahui
Format Book Chapter
LanguageEnglish
Published United Kingdom CRC Press 2024
Taylor & Francis Group
Edition1
Subjects
Cluster Id
Larger Homogenous Regions
Convex Hull
FIPS Code
Minimum Bounding Rectangle
Columns Tab
Row Splitter
Options Tab
Concatenate Node
Expression String
CSV File
Aggregation Method
Length Width Ratio
Input Data Port
Cluster Centroids
Aggregating Census Tracts
Sum Distance
Column Isolate
Measuring Attribute Similarity
Group Column
Spatial Weight Matrix
Cancer Counts
Census Tracts
Column Naming
Online AccessGet full text

Cover

More Information
Summary:Rates of rare events (e.g., cancer, AIDS, homicide) are often subject to the small population (numbers) problem, where the denominators are small or vary a great deal. The problem can lead to unreliable rate estimates, sensitivity to missing data and other data errors, and data suppression in sparsely populated areas. One approach to mitigate the problem is regionalization (or spatial clustering) by grouping smaller areas into larger homogenous regions with comparable population sizes. A case study on mapping breast cancer rates in Louisiana is used to illustrate various regionalization methods such as SKATER, AZP, MaxP, SCHC and REDCAP methods. In addition, the Mixed-Level Regionalization (MLR) method is introduced to decompose areas of large population and merge areas of small population simultaneously to derive regions with comparable population size. A case study on mapping breast cancer rates in Louisiana is used to illustrate various regionalization methods such as SKATER, AZP, MaxP, SCHC and REDCAP methods. In addition, the Mixed-Level Regionalization (MLR) method is introduced to decompose areas of large population and merge areas of small population simultaneously to derive regions with comparable population size.
ISBN:9781032302430
1032302437
DOI:10.1201/9781003304357-9