An empirical evaluation of small area estimators

This paper investigates the comparative performance of five small areaestimators. We use Monte Carlo simulation in the context of boththeoretical and empirical populations. In addition to the direct andindirect estimators, we consider the optimal composite estimator withpopulation weights, and two composite estimators with estimatedweights: one that assumes homogeneity of within area variance andsquare bias, and another one that uses area specific estimates ofvariance and square bias. It is found that among the feasibleestimators, the best choice is the one that uses area specificestimates of variance and square bias.

Location of multiple server common service centers or public facilities for minimizing general congestion and travel cost functions

We propose a model and solution methods, for locating a fixed number ofmultiple-server, congestible common service centers or congestible publicfacilities. Locations are chosen so to minimize consumers congestion (orqueuing) and travel costs, considering that all the demand must be served.Customers choose the facilities to which they travel in order to receiveservice at minimum travel and congestion cost. As a proxy for thiscriterion, total travel and waiting costs are minimized. The travel costis a general function of the origin and destination of the demand, whilethe congestion cost is a general function of the number of customers inqueue at the facilities.

R&D cooperation and spillovers: Some empirical evidence

This paper provides some first empirical evidence on the relationshipbetween R&D spillovers and R&D cooperation. The results suggest disentangling different aspects of know-how flows. Firms which rate incoming spillovers more importantly and who can limit outgoing spillovers by a more effective protection of know-how, are more likely to cooperate in R&D. Our analysis also finds that cooperating firms have higher incoming spillovers and higher protection of know-how, indicating that cooperation may serve as a vehicle to manage information flows. Our results thus suggest that on the one hand the information sharing and coordination aspects of incoming spillovers are crucial in understanding cooperation, while on the other hand, protection against outgoing spillovers is important for firms to engage in stable cooperative agreements by reducing free-rider problems. Distinguishing different types of cooperative partners reveals that while managing outgoing spillovers is less critical in alliances with non-commercial research partners than between vertically related partners, the incoming spillovers seem to be more critical in understanding the former type of R&D cooperation.

Gender specialization in households: An empirical analysis

This paper studies the effect of parental education on the educational attainmentof children in the US for cohorts born after 1910. Importantly, we allow for cohort-specificdifferences by gender. Our estimates show that paternal education has been more importantfor the attainment of male children (paternal specialization on sons). However, maternalspecialization (on daughters) seems to have appeared only for cohorts born after 1955. Weinterpret these results as evidence that fathers are more important role models for sonswhile mothers are a more important reference for daughters. We argue that our results arerobust to the presence of hereditary unobserved ability and conjecture that both types ofgender specialization may have been present in earlier cohorts too.

A data-dependent skeleton estimate and a scale-sensitive dimension for classification

The classical binary classification problem is investigatedwhen it is known in advance that the posterior probability function(or regression function) belongs to some class of functions. We introduceand analyze a method which effectively exploits this knowledge. The methodis based on minimizing the empirical risk over a carefully selected``skeleton'' of the class of regression functions. The skeleton is acovering of the class based on a data--dependent metric, especiallyfitted for classification. A new scale--sensitive dimension isintroduced which is more useful for the studied classification problemthan other, previously defined, dimension measures. This fact isdemonstrated by performance bounds for the skeleton estimate in termsof the new dimension.

Cross-border banking in Europe: An empirical investigation

This paper investigates bilateral trade in banking services within the European Union. The attention has been addressed to two main issues. First, to test the bank's motivations for setting up the different forms of overseas offices, and secondly, to assess the importance of barriers to entry across national European banking systems. Empirical results confirm the existence of different motivations for establishing representative offices, branches and subsidiaries in foreign locations. In addition, evidence has been achieved about the importance of non-regulatory barriers that could make difficult the existence of a single European market for banking services.

Antibiothérapie empirique lors de neutropénie fébrile [Empirical antibiotic therapy for febrile neutropenia]

Immediate broad-spectrum empirical antibacterial therapy is the key of management in febrile neutropenic patients. These patients can be stratified according to the risk of complications with the clinical MASCC score. Patients at low risk of complications can be efficaciously treated with oral antibiotics (e.g. fluoroquinolone and beta-lactam), provided that compliance and drug absorption are adequate. Early discharge is possible if clinical, logistic, and social criteria are fulfilled. Intravenous antibiotic therapy with broad-spectrum beta-lactam antibiotics in the hospital remains the standard in high-risk patients. The empirical addition of an aminoglycoside and/or a glycopeptide is recommended if the local incidence of infections due to beta-lactam resistant pathogens is high or in critically ill septic patients.

The domain and interpretation of utility functions: An exploration

This paper proposes an exploration of the methodology of utilityfunctions that distinguishes interpretation from representation. Whilerepresentation univocally assigns numbers to the entities of the domainof utility functions, interpretation relates these entities withempirically observable objects of choice. This allows us to makeexplicit the standard interpretation of utility functions which assumesthat two objects have the same utility if and only if the individual isindifferent among them. We explore the underlying assumptions of suchan hypothesis and propose a non-standard interpretation according towhich objects of choice have a well-defined utility although individualsmay vary in the way they treat these objects in a specific context.We provide examples of such a methodological approach that may explainsome reversal of preferences and suggest possible mathematicalformulations for further research.

The determinants of football match attendance revisited: Empirical evidence from the Spanish Football League

An attendance equation is estimated using data on individual games playedin the Spanish First Division Football League. The specification includesas explanatory factors: economic variables, quality, uncertainty andopportunity costs. We concentrate the analysis on some specificationissues such as controlling the effect of unobservables given the paneldata structure of the data set, the type of functional form and thepotential endogeneity of prices. We obtain the expected effects onattendance for all the variables. The estimated price elasticities aresmaller than one in absolute value as usually occurs in this literaturebut are sensitive to the specification issues.

Model selection and error estimation

We study model selection strategies based on penalized empirical loss minimization. We point out a tight relationship between error estimation and data-based complexity penalization: any good error estimate may be converted into a data-based penalty function and the performance of the estimate is governed by the quality of the error estimate. We consider several penalty functions, involving error estimates on independent test data, empirical {\sc vc} dimension, empirical {\sc vc} entropy, andmargin-based quantities. We also consider the maximal difference between the error on the first half of the training data and the second half, and the expected maximal discrepancy, a closely related capacity estimate that can be calculated by Monte Carlo integration. Maximal discrepancy penalty functions are appealing for pattern classification problems, since their computation is equivalent to empirical risk minimization over the training data with some labels flipped.

Comparing and validating hypothesis test procedures: Graphical and numerical tools

When the behaviour of a specific hypothesis test statistic is studied by aMonte Carlo experiment, the usual way to describe its quality is by givingthe empirical level of the test. As an alternative to this procedure, we usethe empirical distribution of the obtained \emph{p-}values and exploit itsinformation both graphically and numerically.

Endogeneous matching in university-industry collaboration: Theory and empirical evidence from the UK

We develop a two-sided matching model to analyze collaboration between heterogeneousacademics and firms. We predict a positive assortative matching in terms of both scientificability and affinity for type of research, but negative assortative in terms of ability on one sideand affinity in the other. In addition, the most able and most applied academics and the mostable and most basic firms shall collaborate rather than stay independent. Our predictionsreceive strong support from the analysis of the teams of academics and firms that proposeresearch projects to the UK's Engineering and Physical Sciences Research Council.

MACROPHAGES FROM CROHN'S DISEASE PATIENTS EXHIBIT DEFICIENT REPAIR FUNCTIONS

AbstractBackground: Mucosal healing is becoming a major goal in the treatment of Crohn's disease. It has been previously reported that myeloid cells induce mucosal healing in a mouse model of acute colitis. The aim in this study is to investigate the pro-repair function of myeloid cells in healthy donors (HD) and Crohn's disease patients (CD).Methods: Peripheral blood mononuclear cells (PBMC) from HD and CD patients were isolated from blood samples and tested either directly or after differentiation ex-vivo into macrophages (Μφ). Intestinal macrophages (IMACs) were isolated from the bowel mucosa of patients undergoing intestinal surgical resections. Through an in vitro wound healing assay the repairing ability of these various human myeloid cells and the mechanisms responsible of wound healing were evaluated.Results: PBMC and myeloid CD14+ cells from HD and CD were not able to repair at any tested cell concentration. Μφ from HD and ulcerative colitis (UC) patients were able to induce wound healing and this capacity was partially mediated by Hepatocyte Growth Factor (HGF). Remarkably, CD Μφ were unable to promote wound healing and produced lower levels of HGF as compared to Μφ from HD or UC patients. In particular, Μφ from CD in active phase (ACD) exhibited the weakest repair function, but this defect was rescued if rh- GM-CSF was added during the differentiation of PBMCs. Interestingly, IMACs from HD promoted wound healing and produced HGF.Conclusion: We demonstrated that CD Μφ, unlike HD or UC Μφ, were defective in promoting wound healing, in particular if coming from an ACD. This deficient pro-repair function was related to a lower production of HGF. IMACs from HD colonic mucosa induced wound healing, confirming the results obtained with Μφ. Our results are in keeping with the current theory of CD as an innate immunodeficiency. In this context, Μφ may be responsible for the mucosal repair defects observed in CD patients and for the subsequent chronic activation of the adaptive immune response.

Three essays on liquidity risk

Preface In this thesis we study several questions related to transaction data measured at an individual level. The questions are addressed in three essays that will constitute this thesis. In the first essay we use tick-by-tick data to estimate non-parametrically the jump process of 37 big stocks traded on the Paris Stock Exchange, and of the CAC 40 index. We separate the total daily returns in three components (trading continuous, trading jump, and overnight), and we characterize each one of them. We estimate at the individual and index levels the contribution of each return component to the total daily variability. For the index, the contribution of jumps is smaller and it is compensated by the larger contribution of overnight returns. We test formally that individual stocks jump more frequently than the index, and that they do not respond independently to the arrive of news. Finally, we find that daily jumps are larger when their arrival rates are larger. At the contemporaneous level there is a strong negative correlation between the jump frequency and the trading activity measures. The second essay study the general properties of the trade- and volume-duration processes for two stocks traded on the Paris Stock Exchange. These two stocks correspond to a very illiquid stock and to a relatively liquid stock. We estimate a class of autoregressive gamma process with conditional distribution from the family of non-central gamma (up to a scale factor). This process was introduced by Gouriéroux and Jasiak and it is known as Autoregressive gamma process. We also evaluate the ability of the process to fit the data. For this purpose we use the Diebold, Gunther and Tay (1998) test; and the capacity of the model to reproduce the moments of the observed data, and the empirical serial correlation and the partial serial correlation functions. We establish that the model describes correctly the trade duration process of illiquid stocks, but have problems to adjust correctly the trade duration process of liquid stocks which present long-memory characteristics. When the model is adjusted to volume duration, it successfully fit the data. In the third essay we study the economic relevance of optimal liquidation strategies by calibrating a recent and realistic microstructure model with data from the Paris Stock Exchange. We distinguish the case of parameters which are constant through the day from time-varying ones. An optimization problem incorporating this realistic microstructure model is presented and solved. Our model endogenizes the number of trades required before the position is liquidated. A comparative static exercise demonstrates the realism of our model. We find that a sell decision taken in the morning will be liquidated by the early afternoon. If price impacts increase over the day, the liquidation will take place more rapidly.