A
Alexandra M. Schmidt
Researcher at McGill University
Publications - 90
Citations - 1889
Alexandra M. Schmidt is an academic researcher from McGill University. The author has contributed to research in topics: Covariance & Gaussian process. The author has an hindex of 19, co-authored 75 publications receiving 1636 citations. Previous affiliations of Alexandra M. Schmidt include Institute of Applied Economic Research & Université du Québec à Trois-Rivières.
Papers
More filters
Journal ArticleDOI
Nonstationary Multivariate Process Modeling through Spatially Varying Coregionalization
TL;DR: In this paper, a spatially varying linear model of coregionalization (SVLMC) is proposed for the analysis of multivariate spatial data, which is a generalization of the LMC.
Journal ArticleDOI
Bayesian inference for non-stationary spatial covariance structure via spatial deformations
TL;DR: In this paper, a Bayesian model is proposed to address the anisot- ropy problem, where the correlation function of the spatial process is defined by reference to a latent space, denoted by D, where stationarity and isotropy hold.
Journal ArticleDOI
Modelling species diversity through species level hierarchical modelling
Alan E. Gelfand,Alexandra M. Schmidt,Shanshan Wu,John A. Silander,Andrew M. Latimer,Anthony G. Rebelo +5 more
TL;DR: In this article, a two-stage hierarchical logistic regression model was developed to predict the probability of presence or absence for each species at each cell, given species attributes, grid cell (site level) environmental data with species level coefficients, and a spatial random effect.
Journal ArticleDOI
A Bayesian coregionalization approach for multivariate pollutant data
TL;DR: In this article, the authors proposed a rich class of covariance functions developed through the so-called linear coregionalization model for multivariate spatial observations, which can be used to reparameterize a multiivariate spatial model using suitable univariate conditional spatial processes, facilitating the computation.
Journal ArticleDOI
Considering covariates in the covariance structure of spatial processes
TL;DR: In this paper, the authors relax the assumption of stationary GP by accounting for covariate information in the covariance structure of the process, and propose to use covariates to allow the latent space model of Sampson and Guttorp to be of dimension C < 2.