Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Ekvall, Karl Oskar"'
We show that confidence intervals for a variance component or proportion, with asymptotically correct uniform coverage probability, can be obtained by inverting certain test-statistics based on the score for the restricted likelihood. The results app
Externí odkaz:
http://arxiv.org/abs/2404.15060
Compositional data arise in many areas of research in the natural and biomedical sciences. One prominent example is in the study of the human gut microbiome, where one can measure the relative abundance of many distinct microorganisms in a subject's
Externí odkaz:
http://arxiv.org/abs/2212.09833
Autor:
Ekvall, Karl Oskar, Bottai, Matteo
We propose a unified framework for likelihood-based regression modeling when the response variable has finite support. Our work is motivated by the fact that, in practice, observed data are discrete and bounded. The proposed methods assume a model wh
Externí odkaz:
http://arxiv.org/abs/2203.04582
Autor:
Ekvall, Karl Oskar, Bottai, Matteo
Publikováno v:
Ann. Statist. 50(3): 1806-1832 (June 2022)
We propose confidence regions with asymptotically correct uniform coverage probability of parameters whose Fisher information matrix can be singular at important points of the parameter set. Our work is motivated by the need for reliable inference on
Externí odkaz:
http://arxiv.org/abs/2103.10236
Autor:
Ekvall, Karl Oskar, Molstad, Aaron J.
We propose a new method for multivariate response regression and covariance estimation when elements of the response vector are of mixed types, for example some continuous and some discrete. Our method is based on a model which assumes the observable
Externí odkaz:
http://arxiv.org/abs/2101.08436
Autor:
Ekvall, Karl Oskar
We propose a principal components regression method based on maximizing a joint pseudo-likelihood for responses and predictors. Our method uses both responses and predictors to select linear combinations of the predictors relevant for the regression,
Externí odkaz:
http://arxiv.org/abs/2004.14009
Autor:
Ekvall, Karl Oskar, Jones, Galin L.
We study the convergence properties of a collapsed Gibbs sampler for Bayesian vector autoregressions with predictors, or exogenous variables. The Markov chain generated by our algorithm is shown to be geometrically ergodic regardless of whether the n
Externí odkaz:
http://arxiv.org/abs/1907.03170
Autor:
Ekvall, Karl Oskar, Jones, Galin L.
We present new results for consistency of maximum likelihood estimators with a focus on multivariate mixed models. Our theory builds on the idea of using subsets of the full data to establish consistency of estimators based on the full data. It requi
Externí odkaz:
http://arxiv.org/abs/1810.01203
Autor:
Ekvall, Karl Oskar, Gray, Brian R.
We consider estimation of the covariance matrix of a multivariate normal distribution when the correlation matrix is separable in the sense that it factors as a Kronecker product of two smaller matrices. A computationally convenient coordinate descen
Externí odkaz:
http://arxiv.org/abs/1805.00318
Autor:
Ekvall, Karl Oskar
Publikováno v:
In Journal of Multivariate Analysis July 2022 190