We propose a first-order bias correction term for the Gini index to reduce the bias due to grouping. It depends on only the number of individuals in each group and is derived from a measurement error framework. We also provide a formula for the remaining second-order bias. Both Monte Carlo and EU and U.S. empirical evidence show that the first-order correction reduces a considerable share of the bias, but that some remaining second-order bias is increasing in the variance. We propose a procedure that addresses the remaining second-order bias by using additional information.

background

/pdf/a-simple-correction-to-remove-the-bias-of-the-gini-4qugauqryc.pdf

Mathematics and politics

A Simple Correction to Remove the Bias of the Gini Coefficient due to Grouping

Philippine data are presented which indicate that a contradiction exists between changes induced partly through capital accumulation by the indigenous elite and foreign investment, and both increased political factionalism and declining voting participation. While national elites become more powerful through capital accumulation, local political machines confront structural changes weakening their power. More specialized patron-client structures diminish local elites' ability both to deliver votes to national patrons and to stimulate electoral participation. Growth of the middle class in a stagnant economy increases competition for lucrative local political office Factions proliferate and with the increased concentration of private income, become more dependent on national patronage resources. Unable to meet rising patronage demands, the government resorts to extensive deficit spending which stimulates inflation and further undermines economic growth. The national elite's economic activities thus undermines its authority base as the state becomes increasingly less able to provide security to individuals dislocated by changes generating profit for the elite.

Clientelist Politics in the Philippines: Integration or Instability?*

Questions of healthcare inequities have been of continuing concern to health researchers, planners, and policymakers. The answers to such questions can be difficult to interpret, but deeply affect policy formulation, resource allocation, and our perceptions of the fairness and compassion inherent in the institutions of government and society as a whole. This paper describes the data warehouse implementation of several measures of inequality drawn from the field of economics, including the Gini index. Past research has often focused on using these economic measures to characterize a small set of health status indicators, usually at fairly high levels of aggregation, with comparisons between states or nations. In this research, an ongoing healthcare data warehouse project under the auspices of the Center for Health Outcomes Research at the University of South Florida provides the infrastructure for exploring hundreds of health status indicators at the ZIP code level. The goal is to include information on healthcare inequities in the many reports generated for policymakers throughout Florida.

background or methods

/pdf/measuring-healthcare-inequities-using-the-gini-index-k0lcjdixcc.pdf

Measuring healthcare inequities using the Gini index

Some Practical and Theoretical Problems of Measurement

The relation of different theoretical approaches to one another is a disquieting question in International Relations (IR). Building on recent scholarship addressing the logic of questions and the analytical tools the scholarship provides for investigating the contributions of different explanations this piece argues that any and all explanations are an answer to a contrastive why-question. First, the article presents the objections to eclecticism. It then reviews the application of the logic of questions to IR and develops a “contrast theory” clarifying this logic: Seeking an explanation means delimiting a contrast space within a specific interrogatory context. The article lastly shows how these concepts help in thinking about post-foundational science of IR, that is, a science with no universal epistemological foundation to knowledge. I argue that the pragmatic, problem-driven and complexity-sensitive research agendas are a stronger foundation than currently predominant conceptualizations. An example, drawn from Iran's attempts to acquire nuclear weapons, helps illustrate the value-added by a logic of questions approach.

Mathematics and politics

Citations

A Simple Correction to Remove the Bias of the Gini Coefficient due to Grouping

Clientelist Politics in the Philippines: Integration or Instability?*

Measuring healthcare inequities using the Gini index

Some Practical and Theoretical Problems of Measurement

Analytic Eclecticism in Practice: A Method for Combining International Relations Theories

Related Papers (5)

Entropy and Other Measures of Concentration

On the Measurement of Inequality

The equalization phenomenon: status effects in computer-mediated and face-to-face decision-making groups

Political Order in Changing Societies

Methods of Measuring the Concentration of Wealth