Author
Listed:
- Jean-Marie Dufour
- Tianyu He
Abstract
This paper proposes asymptotically distribution-free inference methods for comparing estimators which admit asymptotically linear Gaussian functional representations across dependent samples. The framework applies to a broad range of welfare indices used in inequality, poverty, and risk analysis. Two distinct situations are considered. First, we propose asymptotic and bootstrap in- tersection methods which are valid under arbitrary dependence between two samples. Second, we focus on the common case of overlapping samples—a special form of dependent samples where sample dependence arises solely from matched pairs—and provide asymptotic and bootstrap meth- ods for comparing indices. We derive consistent estimates for asymptotic variances using the influ- ence function approach. We study the finite-sample performance of the proposed methods through Monte Carlo simulations and find that confidence intervals based on overlapping samples exhibit satisfactory coverage rates and reasonable precision. In contrast, conventional methods based on the assumption of independent samples perform poorly in terms of coverage rates and interval widths. Asymptotic inference can be less reliable when dealing with heavy-tailed distributions, while the bootstrap method provides a viable remedy, unless the variance is substantial or fails to exist. The intersection method yields reliable results with arbitrary dependent samples, including settings in which the overlapping-sample assumptions do not hold. We demonstrate the practical applicability of our proposed methods in analyzing changes in household financial inequality in Italy over time. Cet article propose des méthodes d’inférence asymptotiquement indépendantes de la distribution pour comparer des estimateurs qui admettent des représentations fonctionnelles gaussiennes asymptotiquement linéaires sur des échantillons dépendants. Ce cadre s’applique à un large éventail d’indices de bien-être utilisés dans l’analyse des inégalités, de la pauvreté et des risques. Deux situations distinctes sont examinées. Premièrement, nous proposons des méthodes d’intersection asymptotiques et par bootstrap qui sont valables en présence d’une dépendance arbitraire entre deux échantillons. Ensuite, nous nous concentrons sur le cas courant des échantillons qui se chevauchent — une forme particulière d’échantillons dépendants où la dépendance résulte uniquement de paires appariées — et proposons des méthodes asymptotiques et de bootstrap pour comparer les indices. Nous dérivons des estimations cohérentes des variances asymptotiques à l’aide de l’approche par la fonction d’influence. Nous étudions les performances en échantillon fini des méthodes proposées à l’aide de simulations de Monte Carlo et constatons que les intervalles de confiance basés sur des échantillons chevauchants présentent des taux de couverture satisfaisants et une précision raisonnable. En revanche, les méthodes conventionnelles reposant sur l’hypothèse d’échantillons indépendants affichent de mauvaises performances en termes de taux de couverture et de largeurs d’intervalle. L’inférence asymptotique peut s’avérer moins fiable lorsqu’il s’agit de distributions à queues épaisses, tandis que la méthode du bootstrap offre une solution viable, à moins que la variance ne soit importante ou n’existe pas. La méthode d'intersection fournit des résultats fiables pour des échantillons dépendants arbitraires, y compris dans les cas où les hypothèses relatives au chevauchement des échantillons ne sont pas vérifiées. Nous démontrons l'applicabilité pratique des méthodes que nous proposons en analysant l'évolution des inégalités financières entre les ménages en Italie au fil du temps.
Suggested Citation
Download full text from publisher
More about this item
Keywords
;
;
;
;
;
;
;
;
;
;
;
;
;
;
;
;
;
;
JEL classification:
- C01 - Mathematical and Quantitative Methods - - General - - - Econometrics
- C1 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods and Methodology: General
- C12 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods and Methodology: General - - - Hypothesis Testing: General
- C14 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods and Methodology: General - - - Semiparametric and Nonparametric Methods: General
- C15 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods and Methodology: General - - - Statistical Simulation Methods: General
- D6 - Microeconomics - - Welfare Economics
- D63 - Microeconomics - - Welfare Economics - - - Equity, Justice, Inequality, and Other Normative Criteria and Measurement
- G5 - Financial Economics - - Household Finance
- I3 - Health, Education, and Welfare - - Welfare, Well-Being, and Poverty
- I32 - Health, Education, and Welfare - - Welfare, Well-Being, and Poverty - - - Measurement and Analysis of Poverty
Statistics
Access and download statistics
Corrections
All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:cir:cirwor:2026s-14. See general information about how to correct material in RePEc.
If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.
We have no bibliographic references for this item. You can help adding them by using this form .
If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Webmaster (email available below). General contact details of provider: https://edirc.repec.org/data/ciranca.html .
Please note that corrections may take a couple of weeks to filter through
the various RePEc services.