Abstract
Many aspects of multivariate analysis involve obtaining the precision matrix, i.e., the inverse of the covariance matrix. When the dimension is larger than the sample size, the sample covariance matrix is no longer positive definite, and the inverse does not exist. Under the sparsity assumption on the elements of the precision matrix, the problem can be solved by fitting a Gaussian graphical model with lasso penalty. However, in high-dimensional settings in behavioral sciences, the sparsity assumption does not necessarily hold. The dimensions are often greater than the sample sizes, while they are likely to be comparable in size. Under such circumstances, introducing some covariance structures might solve the issue of estimating the precision matrix. Factor analysis is employed for modeling the covariance structure and the Woodbury identity to find the precision matrix. Different methods are compared such as unweighted least squares and factor analysis with equal unique variances (i.e., the probabilistic principal component analysis), as well as ridge factor analysis with small ridge parameters. Results indicate that they all give relatively small mean squared errors even when the dimensions are larger than the sample size.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bentler, P. M. (1976). Multistructure statistical model applied to factor analysis. Multivariate Behavioral Research, 11, 3–15.
Bickel, P., & Lavina, E. (2008). Covariance regularization by thresholding. Annals of Statistics, 36, 2577–2604.
Byrd, R. H., Lu, P., Nocedal, J., & Zhu, C. (1995). A limited memory algorithm for bound constrained optimization. SIAM Journal on Scientific Computing, 16, 1190–1208.
Engel, J., Buydens, L., & Blanchet, L. (2017). An overview of large-dimensional covariance and precision matrix estimator with applications in chemometrics. Journal of Chemometrics, 31, article e2880.
Friedman, J., Hastie, T., & Tibshirani, R. (2008). Sparse inverse covariance estimation with the graphical lasso. Biostatistics, 9, 432–441.
Friedman, J., Hastie, T. & Tibshirani, R. (2018). Graphical lasso: Estimation of Gaussian graphical models, Version 1.10. https://cran.r-project.org/web/packages/glasso/glasso.pdf
Guttman, L. (1956). Best possible systematic estimates of communalities. Psychometrika, 21, 273–285.
Harville, D. A. (1997). Matrix algebra from a statistician’s perspective. New York: Springer.
Hastie, T., Tibshirani, R., & Wainwright, M. (2015). Statistical learning with sparsity: The lasso and generalizations. Boca Raton, FL: CRC Press.
Hayashi, K., & Bentler, P. M. (2000). On the relations among regular, equal unique variances and image factor analysis. Psychometrika, 65, 59–72.
Hayashi, K., Yuan, K.-H., & Jiang, G. (2019). On extended Guttman condition in high dimensional factor analysis. In M. Wilberg, S. Culpepper, R. Janssen, J. Gonzalez, & D. Molenaar (Eds.), Quantitative psychology: The 83rd annual meeting of the psychometric Society, New York City, 2018 (pp. 221–228). New York: Springer.
Krijnen, W. P. (2006). Convergence of estimates of unique variances in factor analysis, based on the inverse sample covariance matrix. Psychometrika, 71, 193–199.
Lawley, D. N., & Maxwell, A. E. (1971). Factor analysis as a statistical method (2nd ed.). New York: American Elsevier.
MacCallum, R. C., Browne, M. W., & Cai, L. (2007). Factor analysis models as approximations. In R. Cudeck & R. C. MacCallum (Eds.), Factor analysis at 100: Historical developments and future directions (pp. 153–175). Mahwah, NJ: Erlbaum.
Mazumder, R., & Hastie, T. (2012). The graphical lasso: New insights and alternatives. Electronic Journal of Statistics, 6, 2125–2149.
Pourahmadi, M. (2013). High-dimensional covariance estimation. New York: Wiley.
Schneeweiss, H. (1997). Factors and principal components in the near spherical case. Multivariate Behavioral Research, 32, 375–401.
Tipping, M. E., & Bishop, C. M. (1999). Probabilistic principal component analysis. Journal of the Royal Statistical Society, Series B, 61, 611–622.
Yuan, K.-H., & Chan, W. (2008). Structural equation modeling with near singular covariance matrices. Computational Statistics & Data Analysis, 52, 4842–4858.
Yuan, K.-H., & Chan, W. (2016). Structural equation modeling with unknown population distributions: Ridge generalized least squares. Structural Equation Modeling, 23, 163–179.
Acknowledgments
The authors would like to thank Dr. Dylan Molenaar for his careful review of the manuscript and also thank Rachelle Podhorzer for clerical assistance. This work was supported by Grant 31971029 from the National Natural Science Foundation of China.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Hayashi, K., Yuan, KH., Jiang, G. (2020). On the Precision Matrix in Semi-High-Dimensional Settings. In: Wiberg, M., Molenaar, D., González, J., Böckenholt, U., Kim, JS. (eds) Quantitative Psychology. IMPS 2019. Springer Proceedings in Mathematics & Statistics, vol 322. Springer, Cham. https://doi.org/10.1007/978-3-030-43469-4_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-43469-4_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-43468-7
Online ISBN: 978-3-030-43469-4
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)