Estimation equations for multivariate linear models with Kronecker structured covariance matrices

Szczepańska-Álvarez, Anna; Hao, Chengcheng; Liang, Yuli; Rosen, Dietrich von

doi:10.1080/03610926.2016.1165852

Cited by 8 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further years of sampling would permit formal testing of the validity of the assumed separability against an unstructured covariance matrix in our data example. Restrictions on either the spatial or temporal autocorrelation could also be incorporated in such a study, building on the work of Szczepańska-Álvarez et al (2017), as could the inclusion of habitat predictors and an analysis of how the assumed covariance structure affects inference about the regression coefficient β.…”

Section: Discussionmentioning

confidence: 99%

Separable correlation and maximum likelihood

Ekvall¹,

Gray²

2018

Preprint

View full text Add to dashboard Cite

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 descent-type algorithm is developed for maximum likelihood estimation. Simulations indicate our method often gives smaller estimation error than some common alternatives when correlation is separable, and that correctly sized tests for correlation separability can be obtained using a parametric bootstrap. Using dissolved oxygen data from the Upper Mississippi River, we illustrate how our model can lead to interesting scientific findings that may be missed when using competing models.

show abstract

Section: Discussionmentioning

confidence: 99%

Separable correlation and maximum likelihood

Ekvall¹,

Gray²

2018

Preprint

View full text Add to dashboard Cite

show abstract

“…by Lu and Zimmerman (2005) [13], Srivastava et al (2008) [18], [4], Filipiak et al (2018a) [6], Filipiak et al (2020) [5]. In the literature, covariance structures partitioned into four submatrices (Szczepańska-Álvarez et al (2017) [21]) or block compound symmetry covariance structures (Szatrowski et al (1976) [19], Szatrowski et al (1982) [20]) are also analyzed.…”

Section: Introductionmentioning

confidence: 99%