Vignette d'image

Tillé, Yves

Nom
Tillé, Yves
Affiliation principale
Site web
Fonction
Professeur ordinaire
Email
yves.tille@unine.ch
Identifiants
https://libra.unine.ch/handle/123456789/541
_
0000-0003-0904-5523

Résultat de la recherche

Filtres

6342
Réinitialiser les filtres

Paramètres

Voici les éléments 1 - 10 sur 105
  • Publication
    Accès libre
    Gender wage difference estimation at quantile levels using sample survey data
    (2023-09-19)
    Mihaela-Cătălina Anastasiade-Guinand
    ;
    Matei, Alina 
    ;
    Tillé, Yves 
    This paper is motivated by the growing interest in estimating gender wage differences in official statistics. The wage of an employee is hypothetically a reflection of her or his characteristics, such as education level or work experience. It is possible that men and women with the same characteristics earn different wages. Our goal is to estimate the differences between wages at different quantiles, using sample survey data within a superpopulation framework. To do this, we use a parametric approach based on conditional distributions of the wages in function of some auxiliary information, as well as a counterfactual distribution. We show in our simulation studies that the use of auxiliary information well correlated with the wages reduces the variance of the counterfactual quantile estimates compared to those of the competitors. Since, in general, wage distributions are heavy-tailed, the interest is to model wages by using heavy-tailed distributions like the GB2 distribution. We illustrate the approach using this distribution and the wages for men and women using simulated and real data from the Swiss Federal Statistical Office.
  • Publication
    Accès libre
    Some Thoughts on Official Statistic and its Future
    (2021-10-19)
    Tillé, Yves 
    In this article, we share some reflections on the state of statistical science and its evolution in the production systems of official statistics. Data sources and methods are evolving, raising questions about the future of official statistics. The history of the methods used deserves a closer look at the changes that are taking place in the world of official statistics.
  • Publication
    Restriction temporaire
    Spatial Spread Sampling Using Weakly Associated Vectors
    (2020-8-11)
    Jauslin, Raphaël 
    ;
    Tillé, Yves 
    Geographical data are generally autocorrelated. In this case, it is preferable to select spread units. In this paper, we propose a new method for selecting well-spread samples from a finite spatial population with equal or unequal inclusion probabilities. The proposed method is based on the definition of a spatial structure by using a stratification matrix. Our method exactly satisfies given inclusion probabilities and provides samples that are very well spread. A set of simulations shows that our method outperforms other existing methods such as the generalized random tessellation stratified or the local pivotal method. Analysis of the variance on a real dataset shows that our method is more accurate than these two. Furthermore, a variance estimator is proposed.
  • Publication
    Restriction temporaire
    Méthodes d’estimation sur petits domaines avec échantillonnage défini par un seuil d’inclusion
    (2020-6-1)
    Guadarrama, María
    ;
    Molina, Isabel
    ;
    Tillé, Yves 
    L’échantillonnage défini par un seuil d’inclusion est appliqué quand il est trop coûteux ou difficile d’obtenir les informations requises pour un sous-ensemble d’unités de la population et que, par conséquent, ces unités sont délibérément exclues de la sélection de l’échantillon. Si les unités exclues sont différentes des unités échantillonnées pour ce qui est des caractéristiques d’intérêt, les estimateurs naïfs peuvent être fortement biaisés. Des estimateurs par calage ont été proposés aux fins de réduction du biais sous le plan. Toutefois, dans les estimations sur petits domaines, ils peuvent être inefficaces y compris en l’absence d’échantillonnage défini par un seuil d’inclusion. Les méthodes d’estimation sur petits domaines fondées sur un modèle peuvent servir à réduire le biais causé par l’échantillonnage défini par un seuil d’inclusion si le modèle supposé se vérifie pour l’ensemble de la population. Parallèlement, pour les petits domaines, ces méthodes fournissent des estimateurs plus efficaces que les méthodes de calage. Étant donné qu’on obtient les propriétés fondées sur un modèle en supposant que le modèle se vérifie, mais qu’aucun modèle n’est exactement vrai, nous analysons ici les propriétés de plan des procédures de calage et des procédures fondées sur un modèle pour l’estimation de caractéristiques sur petits domaines sous échantillonnage défini par un seuil d’inclusion. Nos conclusions confirment que les estimateurs fondés sur un modèle réduisent le biais causé par un échantillonnage défini par un seuil d’inclusion et donnent des résultats significativement meilleurs en matière d’erreur quadratique moyenne du plan.
  • Publication
    Restriction temporaire
    Small area estimation methods under cut-off sampling
    (2020-6-1)
    Guadarrama, María
    ;
    Molina, Isabel
    ;
    Tillé, Yves 
    Cut-off sampling is applied when there is a subset of units from the population from which getting the required information is too expensive or difficult and, therefore, those units are deliberately excluded from sample selection. If those excluded units are different from the sampled ones in the characteristics of interest, naïve estimators may be severely biased. Calibration estimators have been proposed to reduce the design-bias. However, when estimating in small domains, they can be inefficient even in the absence of cut-off sampling. Model-based small area estimation methods may prove useful for reducing the bias due to cut-off sampling if the assumed model holds for the whole population. At the same time, for small domains, these methods provide more efficient estimators than calibration methods. Since model-based properties are obtained assuming that the model holds but no model is exactly true, here we analyze the design properties of calibration and model-based procedures for estimation of small domain characteristics under cut-off sampling. Our results confirm that model-based estimators reduce the bias due to cut-off sampling and perform significantly better in terms of design mean squared error.
  • Publication
    Accès libre
    Linearisation for Variance Estimation by Means of Sampling Indicators: Application to Non‐response
    (2019-8-19)
    Vallée, Audrey-Anne 
    ;
    Tillé, Yves 
    In order to estimate the variance of estimators in survey sampling, we consider a method in which the estimators are linearized with respect to the basic random variables: the sampling indicator and the response indicator. When a superpopulation model is assumed, the estimators can also be linearized with respect to the variable of interest. This method ensures the derivation of a variance since the estimated parameters are linearized with respect to the random variables directly. It becomes particularly straightforward to construct explicit variance estimators. All sources of randomness are taken into account. The effects caused by the complexity of the estimation method, the calibration and the nonresponse treatment, imputation or reweighting, appear automatically and explicitly in the linearization variables. Through a set of examples, we show the simplicity of the method. Some results regarding the estimation of variance with nonresponse can be obtained in a simpler way than the usual developments. A set of simulations illustrates the proposed methodology.
  • Publication
    Accès libre
    A General Result For Selecting Balanced Unequal Probability Samples From a Stream
    (2019-8-1)
    Tillé, Yves 
    Probability sampling methods were developed in the framework of survey statistics. Recently sampling methods are the subject of a renewed interest for the reduction of the size of large data sets. A particular application is sampling from a data stream. The stream is supposed to be so huge that the data cannot be saved. When a new unit appears, the decision to conserve it or not must be taken directly without examining all the units that already appeared in the stream. In this paper, we examine the existing possible methods for sampling with unequal probabilities from a stream. Next we propose a general result about sampling in several phases from a balanced sample that enables us to propose several new solutions for sampling and multi-phase sampling from a stream. Several new applications of this general result are developed.
  • Publication
    Restriction temporaire
    Deville and Särndal's calibration: revisiting a 25 years old successful optimization problem
    (2019-7-23)
    Devaud, Denis 
    ;
    Tillé, Yves 
    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.