Two-stage Huber estimation

In this paper we propose a new robust estimator in the context of two-stage estimation methods directed towards the correction of endogeneity problems in linear models. Our estimator is a combination of Huber estimators for each of the two stages, with scale corrections implemented using preliminary median absolute deviation estimators. In this way we obtain a two-stage estimation procedure that is an interesting compromise between concerns of simplicity of calculation, robustness and efficiency. This method compares well with other possible estimators such as two-stage least-squares (2SLS) and two-stage least-absolute-deviations (2SLAD), asymptotically and in finite samples. It is notably interesting to deal with contamination affecting more heavily the distribution tails than a few outliers and not losing as much efficiency as other popular estimators in that case, e.g. under normality. An additional originality resides in the fact that we deal with random regressors and asymmetric errors, which is not often the case in the literature on robust estimators.     

The symmetric and asymmetric Choquet integrals on finite spaces for decision making

In this paper, we give a mathematical analysis of symmetric and asymmetric Choquet integrals in the view of decision making in a finite setting. These integrals present two ways of dealing with negative integrands. The analysis is done with the aid of the Möbius and interaction transforms, this last one having an interesting interpretation in multicriteria decision making (MCDM). The last part of the paper shows the application of these two integrals in MCDM.     

A spanning heuristic for the unordered and ordered matching identification problem

The matching identification problem (MIP) is a combinatoric search problem related to the fields of learning from examples, boolean functions, and knowledge acquisition. The MIP involves identifying a single “goal” item from a large set of items. Because there is commonly a cost associated with evaluating each guess, the goal item should be identified in as few guesses as possible. As in most search problems, the items have a similar structure, which allows an evaluation of each guessed item. In other words, each guessed item elicits partial information about the goal item, i.e. how similar the guess is to the goal. With this information the goal is more quickly identified.The unordered MIP has been studied by Mehrez and Steinberg (ORSA J. Comput. 7 (1995) 211) in which they proposed two different types of algorithms. The purpose of the present paper is to suggest an improved Spanning Heuristic algorithm. Its improvement increases as the problem size increases. Further results and comparisons are derived for the unordered and ordered cases.This research shows that when the search space is very large, it is better to inquire from items that are known not to be the goal (they have been ruled out by previous guesses), for the purpose of acquiring more information about the goal. As the search space is narrowed, it is better to guess items that have not been ruled out.     

Stable and visualizable Gaussian parsimonious clustering models

Gaussian mixture model-based clustering is now a standard tool to determine a hypothetical underlying structure in continuous data. However, many usual parsimonious models, despite either their appealing geometrical interpretation or their ability to deal with high dimensional data, suffer from major drawbacks due to scale dependence or unsustainability of the constraints after projection. In this work we present a new family of parsimonious Gaussian models based on a variance-correlation decomposition of the covariance matrices. These new models are stable when projected into the canonical planes and, so, faithfully representable in low dimension. They are also stable by modification of the measurement units of the data and such a modification does not change the model selection based on likelihood criteria. We highlight all these stability properties by a specific graphical representation of each model. A detailed Generalized EM (GEM) algorithm is also provided for every model inference. Then, on biological and geological data, we compare our stable models to standard ones (geometrical models and factor analyzer models), which underlines all the profit to obtain unit-free models.     

Using a capabilities approach to understand poverty and social exclusion of psychiatric survivors

The purpose of this project is to better understand poverty and social exclusion of psychiatric survivors using a capabilities approach to social justice as part of a larger mixed-methods longitudinal study (N=380) in Ontario, Canada. Using thematic coding, four themes emerged: poverty, ‘You just try to survive’; stigma, ‘People treat you like trash’; belonging, ‘You feel like you don’t belong’; and shared concern and advocacy, ‘Everyone deserves housing’. This analysis provides a deeper understanding of poverty and other social determinants of experiences of psychiatric survivors, including the synergism of poverty and social exclusion.     

Factors that Determine or Influence Managerial Innovation in Public Contexts: The Case of Local Performance Management

The use of Performance-Based Management (PBM) by French public organizations has sharply accelerated over the last few years. Moreover, very few studies have analyzed this change. The object of this article is thus to conduct an in-depth analysis of the dynamics of managerial innovation in three French local authorities via the study of the factors that foster the adoption and implementation of PBM by this type of organization. We demonstrate a tendency to overestimate the explanatory power of the neo-institutionalist theories. Indeed, our analysis illustrates a balanced vision of the human, technical and contextual factors at the origin of this type of managerial innovation.     

Testofen,a specialised Trigonella foenum-graecum seed extract reduces age-related symptoms of androgen decrease,increases testosterone levels and improves sexual function in healthy aging males in a double-blind randomised clinical study

This study examined the effect of Testofen, a specialised Trigonella foenum-graecum seed extract on the symptoms of possible androgen deficiency, sexual function and serum androgen concentrations in healthy aging males. This was a double-blind, randomised, placebo-controlled trial involving 120 healthy men aged between 43 and 70 years of age. The active treatment was standardised Trigonella foenum-graecum seed extract at a dose of 600?mg/day for 12 weeks. The primary outcome measure was the change in the Aging Male Symptom questionnaire (AMS), a measure of possible androgen deficiency symptoms; secondary outcome measures were sexual function and serum testosterone. There was a significant decrease in AMS score over time and between the active and placebo groups. Sexual function improved, including number of morning erections and frequency of sexual activity. Both total serum testosterone and free testosterone increased compared to placebo after 12 weeks of active treatment. Trigonella foenum-graecum seed extract is a safe and effective treatment for reducing symptoms of possible androgen deficiency, improves sexual function and increases serum testosterone in healthy middle-aged and older men.     

A general central limit theorem and a subsampling variance estimator for α‐mixing point processes

We establish a central limit theorem for multivariate summary statistics of nonstationary α‐mixing spatial point processes and a subsampling estimator of the covariance matrix of such statistics. The central limit theorem is crucial for establishing asymptotic properties of estimators in statistics for spatial point processes. The covariance matrix subsampling estimator is flexible and model free. It is needed, for example, to construct confidence intervals and ellipsoids based on asymptotic normality of estimators. We also provide a simulation study investigating an application of our results to estimating functions.