Results 91 to 100 of about 15,452 (256)
Partial identification with categorical data and nonignorable missing outcomes
Canadian Journal of Statistics, EarlyView.Abstract Nonignorable missing outcomes are common in real‐world datasets and often require strong parametric assumptions to achieve identification. These assumptions can be implausible or untestable, and so we may wish to forgo them in favour of partially identified models that narrow the set of a priori possible values to an identification region.
Daniel Daly‐Grafstein, Paul Gustafson
wiley +1 more source
Canadian Journal of Statistics, EarlyView.Abstract Homogeneous normalized random measures with independent increments represent a broad class of Bayesian nonparametric priors and thus are widely used. In this article, we obtain the strong law of large numbers, the central limit theorem (CLT), and the functional central limit theorem (fCLT) of such measures when the concentration parameter a ...
Junxi Zhang, Shui Feng, Yaozhong Hu
wiley +1 more source
Image offset density distribution model and recognition of hand knuckle
EURASIP Journal on Image and Video Processing, 2019 The accurate description of hand posture plays an important role in the man-machine interaction involved in coordinated assembly. Knuckle image extraction and recognition are of great significance to refine and enrich hand-pose information.
Shiqiang Yang, Luqi Gong, Dan Qiao
doaj +1 more source
Front Propagation Through a Perforated Wall
Communications on Pure and Applied Mathematics, EarlyView.ABSTRACT We consider a bistable reaction– diffusion equation ut=Δu+f(u)$u_t=\Delta u +f(u)$ on RN${\mathbb {R}}^N$ in the presence of an obstacle K$K$, which is a wall of infinite span with many holes. More precisely, K$K$ is a closed subset of RN${\mathbb {R}}^N$ with smooth boundary such that its projection onto the x1$x_1$‐axis is bounded and that ...
Henri Berestycki +2 more
wiley +1 more source
Dirichlet, Dirichlet Process, and Poisson–Dirichlet as Graphons
We show that the finite Dirichlet distribution, the Dirichlet process, and the Poisson–Dirichlet distribution correspond, under the functor \(F\), to three natural classes of block graphons. This correspondence yields a unified framework linking mass partitions and graphons, and identifies a new family of strongly extreme, infinite-rank graphons ...
openaire +2 more sources
Matrix Dirichlet processes [PDF]
Annales de l'Institut Henri Poincaré, Probabilités et Statistiques, 2019 Matrix Dirichlet processes, in reference to their reversible measure, appear in a natural way in many different models in probability. Applying the language of diffusion operators and the method of boundary equations, we describe Dirichlet processes on the simplex and provide two models of matrix Dirichlet processes, which can be realized by various ...
openaire +4 more sources
A Geometric Characterization of Steady Laminar Flow
Communications on Pure and Applied Mathematics, EarlyView.ABSTRACT We study the steady states of the Euler equations on the periodic channel or annulus. We show that if these flows are laminar (layered by closed non‐contractible streamlines which foliate the domain), then they must be either parallel or circular flows.
Theodore D. Drivas, Marc Nualart
wiley +1 more source
A dependent Bayesian Dirichlet process model for source apportionment of particle number size distribution. [PDF]
Environmetrics, 2023 Baerenbold O +8 more
europepmc +1 more source
Shifting Tides: A Decade of Business Climate Adaptation and Resilience Research (2013–2023)
Corporate Social Responsibility and Environmental Management, EarlyView.ABSTRACT Climate change is causing significant disruptions to the socio‐ecological systems in which organizations operate, presenting unprecedented challenges for businesses across sectors in adapting to shifting environmental conditions and building resilience to extreme weather events.
Domenico Villano +3 more
wiley +1 more source
Nonparametric failure time: Time-to-event machine learning with heteroskedastic Bayesian additive regression trees and low information omnibus Dirichlet process mixtures. [PDF]
Biometrics, 2023 Sparapani RA +4 more
europepmc +1 more source