Vignette d'image

Graf, Eric

Nom
Graf, Eric
Affiliation principale
Identifiants
https://libra.unine.ch/handle/123456789/552

Résultat de la recherche

Filtres

5
5
5
32
Réinitialiser les filtres

Paramètres

Voici les éléments 1 - 5 sur 5
  • Publication
    Métadonnées seulement
    Variance Estimation Using Linearization for Poverty and Social Exclusion Indicators
    (2014-6-27)
    Graf, Eric 
    ;
    Tillé, Yves 
    We have used the generalized linearization technique based on the concept of influence function, as Osier has done (Osier 2009), to estimate the variance of complex statistics such as Laeken indicators. Simulations conducted using the R language show that the use of Gaussian kernel estimation to estimate an income density function results in a strongly biased variance estimate. We are proposing two other density estimation methods that significantly reduce the observed bias. One of the methods has already been outlined by Deville (2000). The results published in this article will help to significantly improve the quality of information on the precision of certain Laeken indicators that are disseminated and compared internationally.
  • Publication
    Métadonnées seulement
    Estimation de variance par linéarisation pour des indices de pauvreté et d’exclusion sociale
    (2014-6-19)
    Graf, Eric 
    ;
    Tillé, Yves 
    Nous avons implémenté la technique de linéarisation généralisée reposant sur le concept de fonction d’influence tout comme l’a fait Osier pour estimer la variance de statistiques complexes telles que les indices de Laeken. Des simulations réalisées avec le langage R montrent que, pour les cas où l’on a recours à une estimation par noyau gaussien de la fonction de densité des revenus considérés, on obtient un fort biais pour la valeur estimée de la variance. On propose deux autres méthodes pour estimer la densité qui diminuent fortement le biais constaté. L’une de ces méthodes a déjà été esquissée par Deville. Les résultats publiés ici permettront une amélioration substantielle de la qualité des informations sur la précision de certains indices de Laeken diffusées et comparées internationalement.
  • Publication
    Métadonnées seulement
    Imputation of income data with generalized calibration procedure and GB2 law: illustration with SILC data
    (2013-8-31)
    Graf, Eric 
    ;
    Tillé, Yves 
    In sample surveys of households and persons, questions about income are often sensitive and thus subject to a higher non-response rate. Nevertheless, the household or personal incomes are among the important variables in surveys of this type. The distribution of such collected incomes is not normal, neither log-normal. Hypotheses of classical regression models to explain the income (or their log) are not fulfilled. Imputations using such models modify the original and true distribution of the data. This is not suitable and may conduct the user to wrong interpretations of results computed from data imputed in this way. The generalized beta distribution of the second kind (GB2) is a four parameters distribution. Empirical studies have shown that it adapts very well to income data. The advantage of a parametric income distribution is that there exist explicit formulae for the inequality measures like the Laeken indicators as functions of the parameters. We present a parametric method of imputation, based on the fit of a GB2 law on the income distribution by the use of suitably adjusted weights obtained by generalized calibration. These weights can compensate for non ignorable non-response that affects the variable of interest. We validate our imputation system on data from the Swiss Survey on Income and Living Conditions (SILC).