Bayesian Analysis

Separable covariance arrays via the Tucker product, with applications to multivariate relational data

Peter D. Hoff

Full-text: Open access

Abstract

Modern datasets are often in the form of matrices or arrays, potentially having correlations along each set of data indices. For example, data involving repeated measurements of several variables over time may exhibit temporal correlation as well as correlation among the variables. A possible model for matrix-valued data is the class of matrix normal distributions, which is parametrized by two covariance matrices, one for each index set of the data. In this article we discuss an extension of the matrix normal model to accommodate multidimensional data arrays, or tensors. We show how a particular array-matrix product can be used to generate the class of array normal distributions having separable covariance structure. We derive some properties of these covariance structures and the corresponding array normal distributions, and show how the array-matrix product can be used to define a semi-conjugate prior distribution and calculate the corresponding posterior distribution. We illustrate the methodology in an analysis of multivariate longitudinal network data which take the form of a four-way array.

Article information

Source
Bayesian Anal., Volume 6, Number 2 (2011), 179-196.

Dates
First available in Project Euclid: 13 June 2012

Permanent link to this document
https://projecteuclid.org/euclid.ba/1339612040

Digital Object Identifier
doi:10.1214/11-BA606

Mathematical Reviews number (MathSciNet)
MR2806238

Zentralblatt MATH identifier
1330.62132

Subjects
Primary: 62F15: Bayesian inference
Secondary: 60E05: Distributions: general theory 62H05: Characterization and structure theory 62H12: Estimation 62J10: Analysis of variance and covariance 62P20: Applications to economics [See also 91Bxx]

Keywords
Gaussian matrix normal multiway data network tensor Tucker decomposition

Citation

Hoff, Peter D. Separable covariance arrays via the Tucker product, with applications to multivariate relational data. Bayesian Anal. 6 (2011), no. 2, 179--196. doi:10.1214/11-BA606. https://projecteuclid.org/euclid.ba/1339612040


Export citation

References

  • Browne, M. W. and Shapiro, A. (1991). "Invariance of covariance structures under groups of transformations." Metrika, 38(6): 345–355.
  • Carvalho, C. M. and West, M. (2007). "Dynamic Matrix-variate Graphical Models." Bayesian Analysis, 2(1): 69–98.
  • Dawid, A. P. (1981). "Some matrix-variate distribution theory: notational considerations and a Bayesian application." Biometrika, 68(1): 265–274.
  • De Lathauwer, L., De Moor, B., and Vandewalle, J. (2000). "A multilinear singular value decomposition"." SIAM Journal on Matrix Analysis and Applications, 21(4): 1253–1278.
  • Dutilleul, P. (1999). "The MLE algorithm for the matrix normal distribution." Journal of Statistical Computation and Simulation, 64(2): 105–123.
  • Galecki, A. (1994). "General class of covariance structures for two or more repeated factors in longitudinal data analysis." Communications in Statistics-Theory and Methods, 23(11): 3105–3119.
  • Kass, R. E. and Wasserman, L. (1995). "A reference Bayesian test for nested hypotheses and its relationship to the Schwarz criterion." J. Amer. Statist. Assoc., 90(431): 928–934.
  • Kolda, T. G. (2006). "Multilinear operators for higher-order decompositions." Technical Report SAND2006-2081, Sandia National Laboratories, Albuquerque, NM and Livermore, CA.
  • Kroonenberg, P. M. (2008). Applied multiway data analysis. Wiley Series in Probability and Statistics. Hoboken, NJ: Wiley-Interscience [John Wiley & Sons]. With a foreword by Willem J. Heiser and Jarqueline Meulman.
  • Lu, N. and Zimmerman, D. L. (2005). "The likelihood ratio test for a separable covariance matrix." Statist. Probab. Lett., 73(4): 449–457.
  • McCullagh, P. (1987). Tensor methods in statistics. Monographs on Statistics and Applied Probability. London: Chapman & Hall.
  • Mitchell, M. W., Genton, M. G., and Gumpertz, M. L. (2006). "A likelihood ratio test for separability of covariances." J. Multivariate Anal., 97(5): 1025–1043.
  • Quintana, J. M. and West, M. (1988). "Time Series Analysis of Compositional Data." In Bernardo, J. M., DeGroot, M. H., Lindley, D. V., and Smith, A. F. M. (eds.), Bayesian Statistics 3, 747–756. Clarendon Press [Oxford University Press].
  • Roy, A. and Khattree, R. (2005). "On implementation of a test for Kronecker product covariance structure for multivariate repeated measures data." Stat. Methodol., 2(4): 297–306.
  • Rubin, D. B. (1984). "Bayesianly justifiable and relevant frequency calculations for the applied statistician." Ann. Statist., 12(4): 1151–1172.
  • Tseng, P. (2001). "Convergence of a block coordinate descent method for nondifferentiable minimization." J. Optim. Theory Appl., 109(3): 475–494.
  • Tucker, L. (1966). "Some mathematical notes on three-mode factor analysis"." Psychometrika, 31(3): 279–311.
  • Tucker, L. R. (1964). "The extension of factor analysis to three-dimensional matrices"." Contributions to mathematical psychology, 109–127.
  • Wang, H. and West, M. (2009). "Bayesian analysis of matrix normal graphical models." Biometrika, 96(4): 821–834.
  • West, M. and Harrison, J. (1997). Bayesian forecasting and dynamic models. Springer Series in Statistics. New York: Springer-Verlag, second edition.

See also

  • Related item: Genevera I. Allen. Comment on article by Hoff. Bayesian Anal., Vol. 6, Iss. 2 (2011), 197-201.
  • Related item: Hedibert Freitas Lopes. Comment on article by Hoff. Bayesian Anal., Vol. 6, Iss. 2 (2011), 203-204.