Rachid Boumahdi

Testing for unit roots using panel data: Application to the French stock market efficiency

Abstract A test for unit roots using panel data is performed, in order to assess efficiency of the French capital market. Our Likelihood Ratio statistic does not reject the random walk hypothesis for stock prices, a necessary condition for market efficiency.

Endogenous Regressors and Correlated Effects

There are several situations in econometric modeling where consistency of parameter estimates is questionable because some explanatory variables may be correlated with the model disturbances. Hence the fundamental exogeneity assumption for the regressors may not be supported by the data, with two implications. First, the source of this correlation might be investigated upon to propose possible corrections. Second, alternative but consistent estimators may be proposed. One of the most well-known source of endogenous regressors is the case of simultaneous equations models, in which some of the regressors in a given equation are the dependent variables in others and consequently are correlated with the disturbances of the equation under consideration. Another cause of correlation between explanatory variables and model disturbances is when the former are subject to measurement errors. Chapter 9 provides a detailed treatment of simultaneity and measurement error issues in the case of panel data. There is however an important reason why regressors may be endogenous in the context of panel data. As discussed in the preceding chapters, accounting for individual unobserved heterogeneity is usually done by incorporating random individual-specific effects to the usual idiosyncratic disturbances of the model. Consequently, regressors must be uncorrelated with these individual effects as well for consistent estimates to be obtained. This assumption of no-correlation has been widely criticized by many authors, among which Mundlak (1978).

The private contractual funding of academic laboratories: a panel data analysis

The article presents new evidence explaining contractual private funding of academic laboratories. We find that public funding crowds out private funding. While private funding increases with publications it decreases with publications corrected for impact.

Nonexpected discrimination: the case of social housing in France

This research is a study of the differences in duration of waiting time between European and non-European households to obtain social housing, drawing on the housing survey carried out by the French National Institute of Statistics and Economic Studies (INSEE, Paris, 2006). The idea here is to bring to light eventual discrimination against non-European households. We show that these households, all else held constant, spend more time on the waiting lists. Appropriate decomposition techniques enable us to demonstrate that a nonnegligible portion of this gap could well be due to discrimination.

Another look on earnings functions: Testing for the demand side

Abstract In this paper, we examine three different specifications of earnings functions based on human capital, Thurows version of a segmented labor market and assignment theory. Using French data and considering education as an endogeneous variable, contrary to Hartog (1985), the human capital and assignment approaches are rejected in favor of the Thurows version of a segmented labor market.

The easiest way to estimate the Oaxaca–Blinder decomposition

This article studies the relation between the Oaxaca–Blinder decomposition and the estimated coefficient of a dummy variable for a linear regression. We calculate the unexplained part of the decomposition from the estimated coefficient of the dummy variable. More precisely, if the exogenous variables are uncorrelated to the dummy variable, the estimated coefficient and its variance give directly the value and the variance of the unexplained part of the decomposition. If the independent variables are correlated a simple relation is obtained. Moreover, we show that the significance of the unexplained part can be deduced from the significance of the estimated coefficient of the dummy variable.

Estimation des modèles à deux régimes avec des données de panel

A procedure for estimating parameters of a sample selection model with endogenous regressors is proposed for the case of panel data. The variance-covariance matrix is computed by adapting the Lee, maddala and Trost [1980] approach to panel data. An application of the model to the computation of returns to education is proposed; the instrumental matrices of Breusch-Mizon-Schmidt [1989] and Amemiya Macurdy [1986] are shown to be superior to the one of Hausman-Taylor [1981].

Les déterminants de la durée d'accès à un logement social

The aim of this paper is to highlight the individual characteristics that affect the duration of obtaining housing. The data used are from the housing survey carried out by Insee (Paris, 2006). The results show that family and social criteria are not the only criteria used by social landlords in the allocation of housing. In particular, rent to the households with low incomes and/or non-European households do not seem to be a priority. Codes JEL : H31, D12, R20.