For 0 < α ≤ 2 and 0 < H < 1, anα-time fractional Brownian motion is an iterated processZ =  {Z(t) = W(Y(t)), t ≥ 0} obtained by taking a fractional Brownian motion {W(t), t ∈ ℝ} with Hurst index0 < H < 1 and replacing the time parameter with astrictly α-stable Lévy process {Y(t), t ≥ 0} in ℝ independent of {W(t), t ∈ R}. It is shown that suchprocesses have natural connections to partial differential equations and, whenY is a stable subordinator, can arise as scaling limit of randomlyindexed random walks. The existence, joint continuity and sharp Hölder conditions in theset variable of the local times of a d-dimensionalα-time fractional Brownian motionX = {X(t), t ∈ ℝ+} defined by X(t) = (X1(t), ...,Xd(t)), where t ≥ 0 andX1, ..., Xdare independent copies of Z, are investigated. Our methods rely on thestrong local nondeterminism of fractional Brownian motion.

The statistical properties of the likelihood ratio test statistic (LRTS) for autoregressive regime-switching models are addressed in this paper. This question is particularly important for estimating the number of regimes in the model. Our purpose is to extend the existing results for mixtures [X. Liu and Y. Shao, Ann. Stat. 31 (2003) 807–832] and hidden Markov chains [E. Gassiat, Ann. Inst. Henri Poincaré 38 (2002) 897–906]. First, we study the case of mixtures of autoregressive models (i.e. independent regime switches). In this framework, we give sufficient conditions to keep the LRTS tight and compute its the asymptotic distribution. Second, we consider the extension of the ideas in Gassiat [Ann. Inst. Henri Poincaré 38 (2002) 897–906] to autoregressive models with regimes switches according to a Markov chain. In this case, it is shown that the marginal likelihood is no longer a contrast function and cannot be used to select the number of regimes. Some numerical examples illustrate the results and their convergence properties.

In this paper, we present a new proof of the celebrated theorem of Kellerer, stating that every integrable process, which increases in the convex order, has the same one-dimensional marginals as a martingale. Our proof proceeds by approximations, and calls upon martingales constructed as solutions of stochastic differential equations. It relies on a uniqueness result, due to Pierre, for a Fokker-Planck equation.

We build confidence balls for the common density s of a real valued sample X1,...,Xn. We use resampling methods to estimate the projection of s onto finite dimensional linear spaces and a model selection procedure to choose an optimal approximation space. The covering property is ensured for all n ≥ 2 and the balls are adaptive over a collection of linear spaces.

If a probability density p(x) (x ∈ ℝk) is bounded and R(t) := ∫e〈x, tu〉p(x)dx < ∞ for some linear functional u and all t ∈ (0,1), then, for each t ∈ (0,1) and all large enough n, the n-fold convolution of the t-tilted density \hbox{$\tilde p_t$}$\begin{array}{}{}_{\mathrm{˜}}\\ {\mathit{p}}_{\mathit{t}}\end{array}$ := e〈x, tu〉p(x)/R(t) is bounded. This is a corollary of a general, “non-i.i.d.” result, which is also shown to enjoy a certain optimality property. Such results and their corollaries stated in terms of the absolute integrability of the corresponding characteristic functions are useful for saddle-point approximations.

The P.O.T. method (Peaks Over Threshold) consists in using the generalized Pareto distribution (GPD) as an approximation for the distribution of excesses over a high threshold. In this work, we use a refinement of this approximation in order to estimate second order parameters of the model using the method of probability-weighted moments (PWM): in particular, this leads to the introduction of a new estimator for the second order parameter ρ, which will be compared to other recent estimators through some simulations. Asymptotic normality results are also proved. Our new estimator of ρ looks especially competitive when  |ρ|  is small.

We prove asymptotic equipartition properties for simple hierarchical structures (modelled as multitype Galton-Watson trees) and networked structures (modelled as randomly coloured random graphs). For example, for large n, a networked data structure consisting of n units connected by an average number of links of order n / log n can be coded by about H × n bits, where H is an explicitly defined entropy. The main technique in our proofs are large deviation principles for suitably defined empirical measures.

In this paper, we are interested in estimation problem for the drift parameters matrices of m independent multivariate diffusion processes. More specifically, we consider the case where the m-parameters matrices are supposed to satisfy some uncertain constraints. Given such an uncertainty, we develop shrinkage estimators which improve over the performance of the maximum likelihood estimator (MLE). Under an asymptotic distributional quadratic risk criterion, we study the relative dominance of the established estimators. Further, we carry out simulation studies for observation periods of small and moderate lengths of time that corroborate the theoretical finding for which shrinkage estimators outperform over the MLE. The proposed method is useful in model assessment and variable selection.

Particle filter algorithms approximate a sequence of distributions by a sequence of empirical measures generated by a population of simulated particles. In the context of Hidden Markov Models (HMM), they provide approximations of the distribution of optimal filters associated to these models. For a given set of observations, the behaviour of particle filters, as the number of particles tends to infinity, is asymptotically Gaussian, and the asymptotic variance in the central limit theorem depends on the set of observations. In this paper we establish, under general assumptions on the hidden Markov model, the tightness of the sequence of asymptotic variances when considered as functions of the random observations as the number of observations tends to infinity. We discuss our assumptions on examples and provide numerical simulations.

We recall necessary notions about the geometry and harmonic analysis on a hyperbolic space and provide lecture notes about homogeneous random functions parameterized by this space. The general principles are illustrated by construction of numerous examples analogous to Euclidean case. We also give a brief survey of the fields parameterized by Euclidean spheres. At the end we give a list of important open questions in hyperbolic case.

(Local) self-similarity is a seminal concept, especially for Euclidean random fields. Westudy in this paper the extension of these notions to manifold indexed fields. We giveconditions on the (local) self-similarity index that ensure the existence of fractionalfields. Moreover, we explain how to identify the self-similar index. We describe a way ofsimulating Gaussian fractional fields.

In the context of self-stabilizing processes, that is processes attracted by their ownlaw, living in a potential landscape, we investigate different properties of the invariantmeasures. The interaction between the process and its law leads to nonlinear stochasticdifferential equations. In [S. Herrmann and J. Tugaut. Electron. J. Probab.15 (2010) 2087–2116], the authors proved that, for linearinteraction and under suitable conditions, there exists a unique symmetric limit measureassociated to the set of invariant measures in the small-noise limit. The aim of thisstudy is essentially to point out that this statement leads to the existence, as the noiseintensity is small, of one unique symmetric invariant measure for the self-stabilizingprocess. Informations about the asymmetric measures shall be presented too. The main keyconsists in estimating the convergence rate for sequences of stationary measures usinggeneralized Laplace’s method approximations.

The dual attainment of the Monge–Kantorovich transport problem is analyzed in a generalsetting. The spaces X,Y are assumed to be polish and equipped with Borelprobability measures μ and ν. The transport costfunction c : X × Y →  [0,∞]  is assumedto be Borel measurable. We show that a dual optimizer always exists, provided we interpretit as a projective limit of certain finitely additive measures. Our methods are functionalanalytic and rely on Fenchel’s perturbation technique.

Let (Sk)k≥1 be the classical Bernoulli random walk on the integer line with jump parametersp ∈ (0,1) andq = 1 − p. The probability distribution of the sojourntime of the walk in the set of non-negative integers up to a fixed time is well-known, butits expression is not simple. By modifying slightly this sojourn time through a particularcounting process of the zeros of the walk as done by Chung & Feller [Proc.Nat. Acad. Sci. USA 35 (1949) 605–608], simpler representationsmay be obtained for its probability distribution. In the aforementioned article, only thesymmetric case (p = q = 1/2) isconsidered. This is the discrete counterpart to the famous Paul Lévy’s arcsine law forBrownian motion.

In the present paper, we write out a representation for this probabilitydistribution in the general case together with others related to the random walk subjectto a possible conditioning. The main tool is the use of generating functions.

In this paper, a new class of Gaussian field is introduced called Lacunary Fractional Brownian Motion. Surprisingly we show that usually their tangent fields are not unique at every point. We also investigate the smoothness of the sample paths of Lacunary Fractional Brownian Motion using wavelet analysis.

In many applications, we assume that two random observations x andy are generated according to independent Poisson distributions\hbox{$\PPP(\lambdaS)$}𝒫(λS)and \hbox{$\PPP(\muT)$}𝒫(μT)and we are interested in performing statistical inference on the ratioφ = λ / μ of the twoincidence rates. In vaccine efficacy trials, x and y aretypically the numbers of cases in the vaccine and the control groups respectively,φ is called the relative risk and the statistical model is called‘partial immunity model’. In this paper we start by defining a natural semi-conjugatefamily of prior distributions for this model, allowing straightforward computation of theposterior inference. Following theory on reference priors, we define the reference priorfor the partial immunity model when φ is the parameter of interest. Wealso define a family of reference priors with partial information on μwhile remaining uninformative about φ. We notice that these priors belongto the semi-conjugate family. We then demonstrate using numerical examples that Bayesiancredible intervals for φ enjoy attractive frequentist properties whenusing reference priors, a typical property of reference priors.

The Lévy transform of a Brownian motion B is the Brownian motionB(1) given by Bt(1) = ∫0tsgn(Bs)dBs; callB(n) the Brownian motion obtained fromB by iterating n times this transformation. Weestablish that almost surely, the sequence of paths (t → Bt(n))n⩾0isdense in Wiener space, for the topology of uniform convergence on compact timeintervals.

This paper derives an explicit approximation for the tail probability of a sum of samplevalues taken without replacement from an unrestricted finite population. The approximationis shown to hold under no conditions in a wide range with relative error given in terms ofthe standardized absolute third moment of the population, β3N. This approximation is used to obtaina result comparable to the well-known Cramér large deviation result in the independentcase, but with no restrictions on the sampled population and an error term depending onlyon β3N. Application to permutation tests isinvestigated giving a new limit result for the tail conditional probability of thestatistic given order statistics under mild conditions. Some numerical results are givento illustrate the accuracy of the approximation by comparing our results to saddlepointapproximations requiring strong conditions.

We investigate the role of the initialization for the stability of the қ-means clusteringalgorithm. As opposed to other papers, we consider the actual қ-means algorithm (also knownas Lloyd algorithm). In particular we leverage on the property that this algorithm can getstuck in local optima of the қ-means objective function. We are interested in the actualclustering, not only in the costs of the solution. We analyze when differentinitializations lead to the same local optimum, and when they lead to different localoptima. This enables us to prove that it is reasonable to select the number of clustersbased on stability scores.

These notes focus on the applications of the stochastic Taylor expansion of solutions of stochastic differential equations to the study of heat kernels in small times. As an illustration of these methods we provide a new heat kernel proof of the Chern–Gauss–Bonnet theorem.