Skip to main content
SpringerLink
Log in

Parsimonious Finite Mixtures of Matrix-Variate Regressions

  • Chapter
  • First Online:
Innovations in Multivariate Statistical Modeling

Part of the book series: Emerging Topics in Statistics and Biostatistics ((ETSB))

Abstract

Over the years, there has been an increased interest in the analysis of matrix-variate data. In the model-based clustering literature, finite mixtures of matrix-variate regressions have been recently introduced. However, a serious concern about this model is the excessive number of parameters associated with the two covariance matrices, related to the responses, for each mixture component. To attain parsimony, the well-known eigen-decomposition is applied to the covariance matrices, yielding a family of 98 different parsimonious mixture models. Parameter estimation, under the maximum likelihood paradigm, is carried out via an expectation-conditional maximization (ECM) algorithm. Our family of models is applied to real data with the aim to assess their clustering performance and for analyzing their behavior with respect to other parsimonious mixture models.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 149.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 199.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 199.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. McNicholas, P. D. (2016). Mixture model-based classification. Boca Raton: Chapman and Hall/CRC Press.

    Book  MATH  Google Scholar 

  2. Murphy, K., & Murphy, T. B. (2020). Gaussian parsimonious clustering models with covariates and a noise component. Advances in Data Analysis and Classification, 14, 293–325.

    Article  MathSciNet  MATH  Google Scholar 

  3. DeSarbo, W. S., & Cron, W. L. (1988). A maximum likelihood methodology for clusterwise linear regression. Journal of classification, 5(2), 249–282.

    Article  MathSciNet  MATH  Google Scholar 

  4. Frühwirth-Schnatter, S. (2006). Finite mixture and Markov switching models. New York: Springer Science & Business Media.

    MATH  Google Scholar 

  5. Dayton, C. M., & Macready, G. B. (1988). Concomitant-variable latent-class models. Journal of the American Statistical Association, 83(401), 173–178.

    Article  MathSciNet  Google Scholar 

  6. Chamroukhi, F. (2017). Skew t mixture of experts. Neurocomputing, 266, 390–408.

    Article  Google Scholar 

  7. Doğru, F. Z., & Arslan, O. (2017). Parameter estimation for mixtures of skew Laplace normal distributions and application in mixture regression modeling. Communications in Statistics-Theory and Methods, 46(21), 10879–10896.

    Article  MathSciNet  MATH  Google Scholar 

  8. Mazza, A., Battisti, M., Ingrassia, S., & Punzo, A. (2019). Modeling return to education in heterogeneous populations: An application to Italy. In I. Greselin, L. Deldossi, L. Bagnato, & M. Vichi (Eds.), Statistical Learning of Complex Data, Studies in Classification, Data Analysis, and Knowledge Organization (pp. 121–131). Switzerland: Springer International Publishing.

    Google Scholar 

  9. Mazza, A., & Punzo, A. (2020). Mixtures of multivariate contaminated normal regression models. Statistical Papers, 61(2), 787–822.

    Article  MathSciNet  MATH  Google Scholar 

  10. Viroli, C. (2011). Model based clustering for three-way data structures. Bayesian Analysis, 6(4), 573–602.

    Article  MathSciNet  MATH  Google Scholar 

  11. Viroli, C. (2011). Finite mixtures of matrix normal distributions for classifying three-way data. Statistics and Computing, 21(4), 511–522.

    Article  MathSciNet  MATH  Google Scholar 

  12. Gallaugher, M. P. B., & McNicholas, P. D. (2018). Finite mixtures of skewed matrix variate distributions. Pattern Recognition, 80, 83–93.

    Google Scholar 

  13. Melnykov, V., Zhu, X., P. D. (2018). On model-based clustering of skewed matrix data. Journal of Multivariate Analysis, 167, 181–194.

    Google Scholar 

  14. Sarkar, S., Zhu, X., Melnykov, V., & Ingrassia, S. (2020). On parsimonious models for modeling matrix data. Computational Statistics & Data Analysis, 142, 106822.

    Article  MathSciNet  MATH  Google Scholar 

  15. Gallaugher, M. P. B., & McNicholas, P. D. (2020). Mixtures of skewed matrix variate bilinear factor analyzers. Advances in Data Analysis and Classification, 14, 415–434.

    Google Scholar 

  16. Tomarchio, S. D., Punzo, A., & Bagnato, L. (2020). Two new matrix-variate distributions with application in model-based clustering. Computational Statistics & Data Analysis, 152, 107050.

    Article  MathSciNet  MATH  Google Scholar 

  17. Tomarchio, S. D., Gallaugher, M. P. B., Punzo, A., & McNicholas, P. D. (2022). Mixtures of matrix-variate contaminated normal distributions. Journal of Computational and Graphical Statistics, 31(2), 413–421.

    Google Scholar 

  18. Melnykov, V., & Zhu, X. (2019). Studying crime trends in the USA over the years 2000–2012. Advances in Data Analysis and Classification, 13(1), 325–341.

    Article  MathSciNet  MATH  Google Scholar 

  19. Tomarchio, S. D., McNicholas, P. D., & Punzo, A. (2021). Matrix normal cluster-weighted models. Journal of Classification, 38(3), 556–575.

    Google Scholar 

  20. Celeux, G., & Govaert, G. (1995). Gaussian parsimonious clustering models. Pattern Recognition, 28(5), 781–793.

    Article  Google Scholar 

  21. Tomarchio, S. D., Punzo, A., & Maruotti, A. (2022). Parsimonious Hidden Markov Models for Matrix-Variate Longitudinal Data. Statistics and Computing, 32(3), 1–18.

    Google Scholar 

  22. Gallaugher, M. P. B., & McNicholas, P. D. (2020). Parsimonious mixtures of matrix variate bilinear factor analyzers. Advanced Studies in Behaviormetrics and Data Science: Essays in honor of Akinori Okada (pp. 177–196).

    Google Scholar 

  23. Schwarz, G. (1978). Estimating the dimension of a model. Annals of Statistics, 6(2), 461–464.

    Article  MathSciNet  MATH  Google Scholar 

  24. Biernacki, C., Celeux, G., & Govaert, G. (2000). Assessing a mixture model for clustering with the integrated completed likelihood. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(7), 719–725.

    Article  Google Scholar 

  25. Murphy, K., & Murphy, T. B. (2020). Gaussian parsimonious clustering models with covariates and a noise component. Advances in Data Analysis and Classification, 14, 293–325.

    Article  MathSciNet  MATH  Google Scholar 

  26. Viroli, C. (2012). On matrix-variate regression analysis. Journal of Multivariate Analysis, 111, 296–309.

    Article  MathSciNet  MATH  Google Scholar 

  27. Meng, X. L., & Rubin, D. B. (1993). Maximum likelihood estimation via the ECM algorithm: A general framework. Biometrika, 80(2), 267–278.

    Article  MathSciNet  MATH  Google Scholar 

  28. Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977). Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society: Series B (Methodological), 39(1), 1–22.

    MathSciNet  MATH  Google Scholar 

  29. Browne, R. P., & McNicholas, P. D. (2014). Estimating common principal components in high dimensions. Advances in Data Analysis and Classification, 8(2), 217–226.

    Article  MathSciNet  MATH  Google Scholar 

  30. Hubert, L., & Arabie, P. (1985). Comparing partitions. Journal of Classification, 2(1), 193–218.

    Article  MATH  Google Scholar 

  31. Murphy, K., & Murphy, T. B. (2020). MoEClust: Gaussian Parsimonious Clustering Models with Covariates and a Noise Component. https://cran.r-project.org/package=MoEClust, R package version 1.3.3.

  32. Zhu, X., Sarkar, S., & Melnykov, V. (2022). MatTransMix: An R package for matrix model-based clustering and parsimonious mixture modeling. Journal of Classification, 39(1), 147–170.

    Google Scholar 

  33. Gallaugher, M. P. B., & McNicholas, P. D. (2017). A matrix variate skew-t distribution. Statistics, 6(1), 160–170.

    Google Scholar 

  34. Gallaugher, M. P. B., & McNicholas, P. D. (2019). Three skewed matrix variate distributions. Statistics & Probability Letters, 145, 103–109.

    Google Scholar 

  35. Sarkar, S., Melnykov, V., & Zhu, X. (2021). Tensor-variate finite mixture modeling for the analysis of university professor remuneration. The Annals of Applied Statistics, 15(2), 1017–1036.

    Article  MathSciNet  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Dipartimento di Economia e Impresa, Università degli Studi di Catania, Catania, Italy

    Antonio Punzo & Salvatore D. Tomarchio

Authors
  1. Antonio Punzo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Salvatore D. Tomarchio
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Antonio Punzo .

Editor information

Editors and Affiliations

  1. Department of Statistics, University of Pretoria, Pretoria, South Africa

    Andriëtte Bekker

  2. Department of Statistics, University of Pretoria, Pretoria, South Africa

    Johannes T. Ferreira

  3. Department of Statistics, Ferdowsi University of Mashhad, Mashhad, Iran

    Mohammad Arashi

  4. Department of Statistics, University of Pretoria, Pretoria, South Africa

    Ding-Geng Chen

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Punzo, A., Tomarchio, S.D. (2022). Parsimonious Finite Mixtures of Matrix-Variate Regressions. In: Bekker, A., Ferreira, J.T., Arashi, M., Chen, DG. (eds) Innovations in Multivariate Statistical Modeling. Emerging Topics in Statistics and Biostatistics . Springer, Cham. https://doi.org/10.1007/978-3-031-13971-0_17

Download citation

Publish with us

Policies and ethics

Search

Navigation