Skip to content

Repository providing code to reproduce results for "Measuring Inequality Beyond the Gini Coefficient May Clarify Conflicting Findings" by Blesch et al. (2022)

kristinblesch/inequality

main
Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 

This is the GitHub repository for the paper "Measuring Inequality Beyond the Gini Coefficient May Clarify Conflicting Findings" by Kristin Blesch, Oliver Hauser & Jon M. Jachimowicz (2022). The paper can be divided into three parts. The respective folders each contain a specific README file that guides through reproducing our results.


Part 1 Lorenz curve estimation using MLE and NLS on a US county and state level. Relevant code can be found in the respective folder including .csv files with estimated Ortega parameters on a US county and state level. You can browse through the interactive visualization of these estimates, or you can have a look at the following Figure for a static preview, where Panel A depicts the Gini coefficient, Panel B Ortega parameter alpha and Panel C Ortega parameter gamma on a US county level.

us_map_figure


Part 2 Ortega Lorenz curve simulation to investigate what features about the income distribution each of the parameters capture. We provide relevant code in this repository and an interactive RShiny tool to facilitate understanding the Ortega parameters and enable users to visually compare various Lorenz curves. rshiny_screenshot          


Part 3 An exploratory study correlating the Ortega parameters to other county-level characteristics. Relevant code is provided in the respective folder. As a visualization of our main results, consider Figure 5 from the paper:

gini_misses_correlations

Figure 5: A two-parameter Ortega approach reveals significant correlations between inequality and policy outcomes that the Gini coefficient misses. Note that the confidence level is 0.9995, using a Bonferroni correction. The figure shows the sub-sample of covariates (33 out of 100) for which the Pearson correlations between county-level variables were not significantly related to the Gini coefficient but exhibited at least one statistically significant (partial) correlation with the Ortega parameters. Abbreviations: M - male; F - female; Q - income quartile; Frac. - fraction; raceadj. - race adjusted

About

Repository providing code to reproduce results for "Measuring Inequality Beyond the Gini Coefficient May Clarify Conflicting Findings" by Blesch et al. (2022)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published