Happy Birthday Iain Johnstone 68 Abstract: motivated by questions from quantitative genetics, we consider high dimensional versions of some common variance component models. We focus on quadratic estimators of 'genetic covariance' and study the behavior of both the bulk of the estimated eigenvalues and the largest estimated eigenvalues in some plausible asymptotic models.
Eigenvalues Variance And Cumulative Variance Of The Principal Leading principal components of g indicate directions of strongest evolutionary response rank of g indicates e ective dimensionality of evolution sparsity of g indicates extent of genetic correlations among traits. View a pdf of the paper titled eigenvalue distributions of variance components estimators in high dimensional random effects models, by zhou fan and iain m. johnstone. Our work is motivated in part by the estimation of components of covariance between multiple pheno typic traits in quantitative genetics, and we specialize our results to common experimental designs that arise in this application. We characterize the behavior of outlier sample eigenvalues and eigenvectors of manova variance components estimators in such models under a high dimensional asymptotic regime.
Eigenvalues Variance And Cumulative Variance Of The Principal Our work is motivated in part by the estimation of components of covariance between multiple pheno typic traits in quantitative genetics, and we specialize our results to common experimental designs that arise in this application. We characterize the behavior of outlier sample eigenvalues and eigenvectors of manova variance components estimators in such models under a high dimensional asymptotic regime. Our work is motivated in part by the estimation of components of covariance between multiple phenotypic traits in quantitative genetics, and we specialize our results to common experimental designs that arise in this application. We focus on quadratic estimators of 'genetic covariance' and study the behavior of both the bulk of the estimated eigenvalues and the largest estimated eigenvalue in some plausible asymptotic models. Our work is motivated by the estimation of components of covariance between multiple phenotypic traits in quantitative genetics, and we specialize our results to common experimental designs that arise in this application. In this setting, relatively little is known about the distribution of the largest eigenvalue, or principal component variance, especially in null cases.
Iain Johnstone Stanford Medicine Our work is motivated in part by the estimation of components of covariance between multiple phenotypic traits in quantitative genetics, and we specialize our results to common experimental designs that arise in this application. We focus on quadratic estimators of 'genetic covariance' and study the behavior of both the bulk of the estimated eigenvalues and the largest estimated eigenvalue in some plausible asymptotic models. Our work is motivated by the estimation of components of covariance between multiple phenotypic traits in quantitative genetics, and we specialize our results to common experimental designs that arise in this application. In this setting, relatively little is known about the distribution of the largest eigenvalue, or principal component variance, especially in null cases.
Eigenvalues Of Components And Total Variance Explained By Components Our work is motivated by the estimation of components of covariance between multiple phenotypic traits in quantitative genetics, and we specialize our results to common experimental designs that arise in this application. In this setting, relatively little is known about the distribution of the largest eigenvalue, or principal component variance, especially in null cases.
Comments are closed.