In this paper we study the asymptotic behaviour of power and multipower variations of stochastic processes. Processes of the type considered serve in particular, to analyse data of velocity increments of a fluid in a turbulence regime with spot intermittency sigma. The purpose of the present...

We contrast two approaches to the prediction of latent variables in the model of factor analysis. The likelihood statistic constitutes the set of minimal sufficient statistics for the unobservables when sampling arises from the exponential family of distributions. Linear predictors on the other...

Lexical parsing is the whole set of techniques to increase from a raw text to a sequence of tagged words ; these tags are morphological and grammatical information. Lexical parsing generally uses an electronic dictionary. But a few of them accommodate themselves to proper nouns that are a...

En traitement automatique de la langue naturelle, l'analyse lexicale d'un texte est faite a partir de dictionnaires electroniques. Ceux-ci comportent tres peu de Noms Propres. Un travail de collecte des toponymes (noms de lieux) et gentiles (noms d'habitants) pour la France a ete mene. 55508...

Develops a robust statistical procedure to analyze the trend in height if the available samples are truncated at the minimum height requirement.

There is an ostensible relationship between whether or not a nation is developed and the interpretation and collection of data in this nation. For instance, if a country is developing, it is difficult to collect figures, though much simpler to interpret them. The opposite is the case in a...

This paper studies the implementation of the coupling from the past (CFTP)method of Propp and Wilson (1996) in the set-up of two and three component mixtures with known components. We show that monotonicity structures can be exhibited in both cases, but that CFTP an still be costly for three...

Many historians now reject quantitative methods as inappropriate to understanding past societies. It is argued here, however, that no sharp distinction between qualitative and quantitative concepts can be drawn, as almost any concept used to describe a past society is implicitly quantitative....

Time heterogeneity, or the fact that subjects are measured at different times, occurs frequently in non-experimental situations. For time heterogeneous data having error components regression structure it is demonstrated that under customary normality assumptions there is no estimation method...