Voici les éléments 1 - 10 sur 12
  • Publication
    Restriction temporaire
    Deville and Särndal's calibration: revisiting a 25 years old successful optimization problem
    In 1992, in a famous paper, Deville and Särndal proposed the calibration method in order to adjust samples on known population totals. This paper had a very important impact in the theory and practise of survey statistics. In this paper, we propose a rigorous formalization of the calibration problem viewed as an optimization problem. We examine the main calibration functions and we discuss the question of the existence of solutions. We also propose an alternate way of solving the optimization problem given by the calibration principle. We finally present a set of simulations in order to compare the different methods.
  • Publication
    Accès libre
    Decomposition of Gender Wage Inequalities through Calibration: Application to the Swiss Structure of Earnings Survey
    This paper proposes a new approach to decompose the wage difference between men and women that is based on a calibration procedure. This approach generalizes two current decomposition methods that are re-expressed using survey weights. The first one is the Blinder-Oaxaca method and the second one is a reweighting method proposed by DiNardo, Fortin and Lemieux. The new approach provides a weighting system that enables us to estimate such parameters of interest like quantiles. An application to data from the Swiss Structure of Earnings Survey shows the interest of this method.
  • Publication
    Métadonnées seulement
    Gender Wage Inequalities in Switzerland: the Public versus the Private Sector
    Wage differences between women and men can be divided into an explained part and an unexplained part. The former encompasses differences in the observable characteristics of the members of groups, such as age, education or work experience. The latter includes the part of the difference that is not attributable to objective factors and represents an estimation of the discrimination level. We discuss the original method of Blinder (J Hum Resour 8(4):436–455, 1973) and Oaxaca (Int Econ Rev 14(3):693–709, 1973), the reweighting technique of DiNardo et al. (Econometrica 64(5):1001–1044, 1996) and our approach based on calibration. Using a Swiss dataset from 2012, we compare the estimated explained and unexplained parts of the difference in average wages in the private and public sectors obtained with the three methods. We show that for the private sector, all three methods yield similar results. For the public sector, the reweighting technique estimates a lower value of the unexplained part than the other two methods. The calibration approach and the reweighting technique allow us to estimate the explained and unexplained parts of the wage differences at points other than the mean. By using this, in this paper, the assumption that wages are more equitable in the public sector is analysed. Wage differences at different quantiles in both sectors are examined. We show that in the public sector, discrimination occurs quite uniformly both in lower and in higher-paying jobs. On the other hand, in the private sector, discrimination is greater in lower-paying jobs than in higher-paying jobs.queryPlease check and confirm the given name and family name is correctly identified for the first author and amend if necessary.
  • Publication
    Métadonnées seulement
    Using a GB2 distribution to estimate gender wage discrimination
    The generalized beta of the second kind (GB2) distribution was used in the literature to model wages. It is a distribution characterized by three shape parameters and a scale parameter. McDonald (1984) showed that it performs better in terms of adjusting wages than other distributions, such as Singh-Maddala or generalized gamma. We investigate a slightly changed version of the GB2 by introducing covariates in one of the parameters. The scale parameter takes the form of an exponential function which accounts for the characteristics of the observed individuals. Conditional to their characteristics, each individual wage has its own distribution. The assumption that all wages follow the same distribution GB2 is thus relaxed. The proposed method is used to model the wages of Swiss men and women in 2010. A counterfactual wage distribution is then built, by using the characteristics of men but the estimated parameters of women. This artificial wage distribution represents the distribution of wages of women, if they had the same characteristics of men. The purpose is to quantify to what extent gender discrimination occurs.
  • Publication
    Métadonnées seulement
    L'estimation de la discrimination salariale en Suisse au travers d'une approche par calage
    En Suisse, la discrimination salariale à l'encontre des femmes existe encore, même si elle est interdite par la loi. Plusieurs méthodes ont été proposées pour mesurer les niveaux de discrimination. Trois méthodes sont discutées, dont deux sont déjà bien établies dans la littérature : la méthode de Blinder et Oaxaca et celle de DiNardo, Fortin et Lemieux. La méthode de Blinder et Oaxaca fut la première à être proposée. Plusieurs autres techniques ont ensuite été suggérées. Ces méthodes consistent à établir un modèle entre les salaires et les caractéristiques des salariés comme l'âge, l'ancienneté ou le niveau de formation. La méthode de Blinder et Oaxaca permet de mesurer la discrimination salariale en décomposant les différences entre les salaires moyens en une partie explicable par les caractéristiques des individus et une partie non explicable due à la discrimination. La méthode de DiNardo, Fortin et Lemieux est basée sur une technique de repondération des caractéristiques d'un groupe afin de les rendre identiques à ceux de l'autre groupe. Avec cette méthode, on peut mesurer la discrimination non seulement pour d'autres paramètres comme des quantiles. Cependant, cette méthode ne réussit pas à rendre les distributions des caractéristiques identiques. La troisième méthode que nous proposons est basée sur une approche par calage. Cette approche résout les problèmes rencontrés par les deux premières méthodes. En utilisant le calage, on s'assure que les distributions des caractéristiques sont identiques et on parvient aussi à estimer la discrimination salariale non seulement pour des moyennes, mais aussi pour des quantiles.
  • Publication
    Métadonnées seulement