The definition and modeling of customer loyalty have been central issues in customer relationship management since many years. Recent papers propose solutions to detect customers that are becoming less loyal, also called churners. The churner status is then defined as a function of the volume of...

Valuing customers is a central issue for any commercial activity. The customer lifetime value (CLV) is the discounted value of the future profits that this customer yields to the company. In order to compute the CLV, one needs to predict the future number of transactions a customer will make and...

In biostatistical practice, it is common to use information criteria as a guide for model selection. We propose new versions of the Focussed Information Criterion (FIC) for variable selection in logistic regression. The FIC gives, depending on the quantity to be estimated, possibly different...

Valuing customers is a central issue for any commercial activity. The customer lifetime value (CLV) is the discounted value of the future profits that this customer yields to the company. In order to compute the CLV, one needs to predict the future number of transactions a customer will make and...

Opening, lunch and closing of financial markets induce a periodic component in the volatility of high-frequency returns. We show that price jumps cause a large bias in the classical periodicity estimators and propose robust alternatives. We find that accounting for periodicity greatly improves...

Quadratic covariation is a popular descriptive measure for the volatility of a multivariate price process. It is consistently estimated by the sum of outer products of high-frequency returns.The proposed Realized Outlyingness Weighted Covariation (ROWCov) is a \emph{weighted} sum of outer...

Modied Value at Risk (VaR) is an estimator of VaR based on the Cornish-Fisher expansion. It is fast to compute and reliable for non-normal returns. In this paper, we introduce modified Expected Shortfall as a new analytical estimator for Expected Shortfall (ES), another popular measure of...

The L <Subscript>1</Subscript>-median is a robust estimator of multivariate location with good statistical properties. Several algorithms for computing the L <Subscript>1</Subscript>-median are available. Problem specific algorithms can be used, but also general optimization routines. The aim is to compare different algorithms with respect...</subscript></subscript>

L’analyse de données spatiales permet d’appréhender des phénomènes en général ignorés de l’analyse économique standard. Dans le cadre du marché du travail, en particulier, l’approche spatiale peut révéler l’importance de la concentration spatiale du chômage, les...