Hostname: page-component-89b8bd64d-j4x9h Total loading time: 0 Render date: 2026-05-08T19:58:34.134Z Has data issue: false hasContentIssue false
  • English
  • Français

STREAMLINED SOLUTIONS TO MULTILEVEL SPARSE MATRIX PROBLEMS

Part of: Numerical linear algebra

Published online by Cambridge University Press:  01 June 2020

TUI H. NOLAN Open the ORCID record for TUI H. NOLAN [Opens in a new window]  and
MATT P. WAND Open the ORCID record for MATT P. WAND [Opens in a new window]
TUI H. NOLAN
Affiliation:
University of Technology Sydney, P.O. Box 123, Broadway, New South Wales2007, Australia email tui.h.nolan@student.uts.edu.au, matt.wand@uts.edu.au
MATT P. WAND*
Affiliation:
University of Technology Sydney, P.O. Box 123, Broadway, New South Wales2007, Australia email tui.h.nolan@student.uts.edu.au, matt.wand@uts.edu.au
*
✉matt.wand@uts.edu.au
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the 'Save PDF' action button.

We define and solve classes of sparse matrix problems that arise in multilevel modelling and data analysis. The classes are indexed by the number of nested units, with two-level problems corresponding to the common situation, in which data on level-1 units are grouped within a two-level structure. We provide full solutions for two-level and three-level problems, and their derivations provide blueprints for the challenging, albeit rarer in applications, higher-level versions of the problem. While our linear system solutions are a concise recasting of existing results, our matrix inverse sub-block results are novel and facilitate streamlined computation of standard errors in frequentist inference as well as allowing streamlined mean field variational Bayesian inference for models containing higher-level random effects.

Keywords

best linear unbiased predictionlinear mixed modelslongitudinal data analysispanel datasmall-area estimationvariational inference

MSC classification

Primary: 65F05: Direct methods for linear systems and matrix inversion

Information

Type
Research Article
Information
The ANZIAM Journal , Volume 62 , Issue 1 , January 2020 , pp. 18 - 41
Copyright
© 2020 Australian Mathematical Society

References

Baltagi, B. H., Econometric analysis of panel data (John Wiley & Sons, Chichester, 2013).Google Scholar
Fitzmaurice, G., Davidian, M., Verbeke, G. and Molenberghs, G. (eds), Longitudinal data analysis (Chapman & Hall/CRC, Boca Raton, FL, 2008); doi:10.1201/9781420011579.CrossRefGoogle ScholarPubMed
Gentle, J. E., Matrix algebra (Springer, New York, 2007); doi:10.1007/978-0-387-70873-7.CrossRefGoogle Scholar
Goldstein, H., Multilevel statistical models, 4th edn (John Wiley & Sons, Chichester, 2010); doi:10.1002/9780470973394.CrossRefGoogle Scholar
Harville, D. A., Matrix algebra from a statistician’s perspective (Springer, New York, 2008).Google Scholar
Henderson, C. R., “Best linear unbiased estimation and prediction under a selection model”, Biometrics 31 (1975) 423–447; doi:10.2307/2529430.CrossRefGoogle Scholar
Hołubowski, W., Kurzyk, D. and Trawiński, T., “A fast method for computing the inverse of symmetric block arrowhead matrices”, Appl. Math. Inf. Sci. 9 (2015) 319–324; doi:10.12785/amis/092L06.Google Scholar
Longford, N. T., “A fast scoring algorithm for maximum likelihood estimation in unbalanced mixed models with nested random effects”, Biometrika 74 (1987) 817–827; doi:10.1093/biomet/74.4.817.CrossRefGoogle Scholar
McCulloch, C. E., Searle, S. R. and Neuhaus, J. M., Generalized, linear, and mixed models, 2nd edn (John Wiley & Sons, Hoboken, NJ, 2008).Google Scholar
Nolan, T. H., Menictas, M. and Wand, M. P., Streamlined computing for variational inference with higher level random effects. arXiv:1903.06616v3 (2020).Google Scholar
Pinheiro, J. C. and Bates, D. M., Mixed-effects models in S and S-PLUS (Springer, New York, 2000); doi:10.1007/978-1-4419-0318-1.CrossRefGoogle Scholar
Rao, J. N. K. and Molina, I., Small area estimation, 2nd edn (John Wiley & Sons, Hoboken, NJ, 2015); doi:10.1002/9781118735855.CrossRefGoogle Scholar
Saberi Nejafi, S., Edalatpanah, S. A. and Gravvanis, G. A., “An efficient method for computing the inverse of arrowhead matrices”, Appl. Math. Lett. 33 (2014) 1–5; doi:10.1016/j.aml.2014.02.010.CrossRefGoogle Scholar
Stanimirović, P. S., Katsikis, V. N. and Kolundžija, D., “Inversion and pseudoinversion of block arrowhead matrices”, Appl. Math. Comput. 341 (2019) 379–401; doi:10.1016/j.amc.2018.09.006.Google Scholar