Karl Oskar Ekvall
YOU?
Author Swipe
View article: Universal inference for variance components
Universal inference for variance components Open
We consider universal inference in variance components models, focusing on settings where the parameter is near or at the boundary of the parameter set. Two cases, which are not handled by existing state-of-the-art methods, are of particul…
View article: Fast and reliable confidence intervals for a variance component
Fast and reliable confidence intervals for a variance component Open
We show that confidence intervals in a variance component model, with asymptotically correct uniform coverage probability, can be obtained by inverting certain test-statistics based on the score for the restricted likelihood. The results a…
View article: Direct covariance matrix estimation with compositional data
Direct covariance matrix estimation with compositional data Open
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…
View article: Mediation by Thyroid Hormone in the Relationships Between Gestational Exposure to Methylmercury and Birth Size
Mediation by Thyroid Hormone in the Relationships Between Gestational Exposure to Methylmercury and Birth Size Open
Our previous studies have linked gestational methylmercury exposure, originating from seafood, to changes in maternal thyroid hormones and infant birth size in a Swedish birth cohort. Herein we aimed to determine associations between mater…
View article: Direct covariance matrix estimation with compositional data
Direct covariance matrix estimation with compositional data Open
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…
View article: Concave Likelihood-Based Regression with Finite-Support Response Variables
Concave Likelihood-Based Regression with Finite-Support Response Variables Open
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…
View article: Confidence regions near singular information and boundary points with applications to mixed models
Confidence regions near singular information and boundary points with applications to mixed models Open
We propose confidence regions with asymptotically correct uniform coverage\nprobability of parameters whose Fisher information matrix can be singular at\nimportant points of the parameter set. Our work is motivated by the need for\nreliabl…
View article: Mixed‐type multivariate response regression with covariance estimation
Mixed‐type multivariate response regression with covariance estimation Open
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…
View article: Targeted principal components regression
Targeted principal components regression Open
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 …
View article: Concave likelihood-based regression with finite-support response variables
Concave likelihood-based regression with finite-support response variables Open
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…
View article: Confidence Regions Near Singular Information and Boundary Points With Applications to Mixed Models
Confidence Regions Near Singular Information and Boundary Points With Applications to Mixed Models Open
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 i…
View article: A unified method for multivariate mixed-type response regression
A unified method for multivariate mixed-type response regression Open
We propose a new method for multivariate response regressions where the elements of the response vector can be of mixed types, for example some continuous and some discrete. Our method is based on a model which assumes the observable mixed…
View article: Mixed-type multivariate response regression with covariance estimation
Mixed-type multivariate response regression with covariance estimation Open
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…
View article: Convergence analysis of a collapsed Gibbs sampler for Bayesian vector autoregressions
Convergence analysis of a collapsed Gibbs sampler for Bayesian vector autoregressions Open
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 wh…
View article: Joint Likelihood-based Principal Components Regression
Joint Likelihood-based Principal Components Regression Open
We propose a method for estimating principal components regressions by maximizing a multivariate normal joint likelihood for responses and predictors. In contrast to classical principal components regression, our method uses information in…
View article: Targeted Principal Components Regression
Targeted Principal Components Regression Open
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 …
View article: Consistent maximum likelihood estimation using subsets with applications to multivariate mixed models
Consistent maximum likelihood estimation using subsets with applications to multivariate mixed models Open
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 dat…
View article: Topics in Multivariate Statistics with Dependent Data
Topics in Multivariate Statistics with Dependent Data Open
University of Minnesota Ph.D. dissertation.February 2019. Major: Statistics. Advisor: Galin Jones. 1 computer file (PDF); vii, 120 pages.
View article: Separable correlation and maximum likelihood
Separable correlation and maximum likelihood Open
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 coordi…