Quite often, observed income and survival data are incomplete due to left- or right-censoring or truncation. Measuring inequality, for instance by the Gini index of concentration, from incomplete data like this will produce biased results. We describe the Stata package GiniInc, which contains three independent functions to estimate the Gini concentration index under different conditions. First, survgini computes a test statistic for the comparison of two (survival) distributions based on the non-parametric estimation of the restricted Gini index for right-censored data, using both asymptotic and permutation inference. Second, survbound computes non-parametric bounds for the unrestricted Gini index from censored data. Finally, survlsl implements maximum likelihood estimation for three commonly used parametric models to estimate the unrestricted Gini Index, both from censored and truncated data. We briefly discuss the methods, describe the package, and illustrate its use through simulated data and examples from an oncology and a historical income study.

GiniInc: a Stata package for measuring inequality from incomplete income and survival data

HONG, LONG
;
Alfani, Guido;Gigliarano, Chiara;Bonetti, Marco
2018

Abstract

Quite often, observed income and survival data are incomplete due to left- or right-censoring or truncation. Measuring inequality, for instance by the Gini index of concentration, from incomplete data like this will produce biased results. We describe the Stata package GiniInc, which contains three independent functions to estimate the Gini concentration index under different conditions. First, survgini computes a test statistic for the comparison of two (survival) distributions based on the non-parametric estimation of the restricted Gini index for right-censored data, using both asymptotic and permutation inference. Second, survbound computes non-parametric bounds for the unrestricted Gini index from censored data. Finally, survlsl implements maximum likelihood estimation for three commonly used parametric models to estimate the unrestricted Gini Index, both from censored and truncated data. We briefly discuss the methods, describe the package, and illustrate its use through simulated data and examples from an oncology and a historical income study.
2018
Hong, Long; Alfani, Guido; Gigliarano, Chiara; Bonetti, Marco
File in questo prodotto:
File Dimensione Formato  
GiniInc_Revision_R1.pdf

non disponibili

Descrizione: Preprint dell'articolo
Tipologia: Documento in Pre-print (Pre-print document)
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 443.52 kB
Formato Adobe PDF
443.52 kB Adobe PDF   Visualizza/Apri
Email-ACCEPT-28APR2018.pdf

non disponibili

Descrizione: Acceptance Email form Journal
Tipologia: Allegato per valutazione Bocconi (Attachment for Bocconi evaluation)
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 65.21 kB
Formato Adobe PDF
65.21 kB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11565/4008468
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 4
social impact