Advertisement

Computational Statistics

, Volume 34, Issue 1, pp 323–347 | Cite as

Shape mixtures of skew-t-normal distributions: characterizations and estimation

  • Mostafa Tamandi
  • Ahad Jamalizadeh
  • Tsung-I LinEmail author
Original Paper
  • 94 Downloads

Abstract

This paper introduces the shape mixtures of the skew-t-normal distribution which is a flexible extension of the skew-t-normal distribution as it contains one additional shape parameter to regulate skewness and kurtosis. We study some of its main characterizations, showing in particular that it is generated through a mixture on the shape parameter of the skew-t-normal distribution when the mixing distribution is normal. We develop an Expectation Conditional Maximization Either algorithm for carrying out maximum likelihood estimation. The asymptotic standard errors of estimators are obtained via the information-based approximation. The numerical performance of the proposed methodology is illustrated through simulated and real data examples.

Keywords

Asymmetry ECME algorithm Observed information matrix Robustness Skew-symmetric Truncated normal 

Notes

Acknowledgements

We gratefully acknowledge the chief editor, the associate editor and two anonymous referees for their valuable comments and suggestions, which led to a greatly improved version of this article. This research was supported by MOST 105-2118-M-005-003-MY2 awarded by the Ministry of Science and Technology of Taiwan.

Supplementary material

180_2018_835_MOESM1_ESM.pdf (538 kb)
Supplementary material 1 (pdf 537 KB)

References

  1. Adcock C, Eling M, Loperfido N (2015) Skewed distributions in finance and actuarial science: a review. Eur J Financ 21:1253–1281CrossRefGoogle Scholar
  2. Aitken AC (1927) On Bernoulli’s numerical solution of algebraic equations. Proc R Soc Edinb 46:289–305CrossRefzbMATHGoogle Scholar
  3. Akaike H (1973) Information theory and an extension of the maximum likelihood principle. In: Petrov BN, Csaki F (eds) 2nd International symposium on information theory. Akademiai Kiado, Budapest, pp 267–281Google Scholar
  4. Anscombe FJ, Glynn WJ (1983) Distribution of the kurtosis statistic \(b_2\) for normal statistics. Biometrika 70:227–234MathSciNetzbMATHGoogle Scholar
  5. Arellano-Valle RB, Castro LM, Genton MG, Gómez HW (2008) Bayesian inference for shape mixtures of skewed distributions, with application to regression analysis. Bayesian Ana 3:513–540MathSciNetCrossRefzbMATHGoogle Scholar
  6. Arellano-Valle RB, G ómez HW, Quintana FA (2004) A new class of skew-normal distributions. Commun Stat Theory Methods 33:1465–1480MathSciNetCrossRefzbMATHGoogle Scholar
  7. Azzalini A (1985) A class of distributions which includes the normal ones. Scand J Stat 12:171–178MathSciNetzbMATHGoogle Scholar
  8. Azzalini A with the collaboration of Capitanio A (2014) The skew-normal and related families, IMS monographs. Cambridge University Press, CambridgeGoogle Scholar
  9. Azzalini A, Capitaino A (2003) Distributions generated by perturbation of symmetry with emphasis on a multivariate skew \(t\)-distribution. J R Stat Soc B 65:367–389MathSciNetCrossRefzbMATHGoogle Scholar
  10. Branco MD, Dey DK (2001) A general class of multivariate skew-elliptical distributions. J Multivar Anal 79:99–113MathSciNetCrossRefzbMATHGoogle Scholar
  11. Cramér H (1946) Mathematical methods of statistics. Princeton University Press, PrincetonzbMATHGoogle Scholar
  12. Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data via the EM algorithm (with discussion). J R Stat Soc B 39:1–38zbMATHGoogle Scholar
  13. D’Agostino RB (1970) Transformation to normality of the null distribution of g1. Biometrika 57:679–681zbMATHGoogle Scholar
  14. Efron B, Hinkley DV (1978) Assessing the accuracy of the maximum likelihood estimator: observed versus expected Fisher information. Biometrika 65:457–482MathSciNetCrossRefzbMATHGoogle Scholar
  15. Efron B, Tibshirani R (1986) Bootstrap methods for standard errors, confidence intervals, and other measures of statistical accuracy. Stat Sci 1:54–75MathSciNetCrossRefzbMATHGoogle Scholar
  16. Eling M (2012) Fitting insurance claims to skewed distributions: are the skew-normal and skew-student good models? Insur Math Econ 51:239–248MathSciNetCrossRefGoogle Scholar
  17. Eling M (2014) Fitting asset returns to skewed distributions: are the skew-normal and skew-student good models? Insur Math Econ 59:45–56MathSciNetCrossRefzbMATHGoogle Scholar
  18. Ferreira CS, Bolfarine H, Lachos VH (2011) Skew scale mixture of normal distributions: properties and estimation. Stat Method 8:154–171MathSciNetCrossRefzbMATHGoogle Scholar
  19. Gómez HW, Venegas O, Bolfarine H (2007) Skew-symmetric distributions generated by the distribution function of the normal distribution. Environmetrics 18:395–407MathSciNetCrossRefGoogle Scholar
  20. Ho HJ, Lin TI, Chang HH, Haase HB, Huang S, Pyne S (2012a) Parametric modeling of cellular state transitions as measured with flow cytometry different tissues. BMC Bioinform 13:S5CrossRefGoogle Scholar
  21. Ho HJ, Pyne S, Lin TI (2012b) Maximum likelihood inference for mixtures of skew student-\(t\)-normal distributions through practical EM-type algorithms. Stat Comput 22:287–299MathSciNetCrossRefzbMATHGoogle Scholar
  22. Huber PJ (1967) The behavior of maximum likelihood estimates under nonstandard conditions. In: Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, vol 1. University of California Press, Berkeley, pp 221–233Google Scholar
  23. Jamalizadeh A, Lin TI (2017) A general class of scale-shape mixtures of skew-normal distributions: properties and estimation. Comput Stat 32:451–474MathSciNetCrossRefzbMATHGoogle Scholar
  24. Lin TI, Lee JC, Yen SY (2007) Finite mixture modelling using the skew normal distribution. Stat Sin 17:909–927MathSciNetzbMATHGoogle Scholar
  25. Lin TI, Ho HJ, Lee CR (2014) Flexible mixture modelling using the multivariate skew-t-normal distribution. Stat Comput 24:531–546MathSciNetCrossRefzbMATHGoogle Scholar
  26. Liu CH, Rubin DB (1994) The ECME algorithm: a simple extension of EM and ECM with faster monotone convergence. Biometrika 81:633–648MathSciNetCrossRefzbMATHGoogle Scholar
  27. Meng XL, Rubin DB (1993) Maximum likelihood estimation via the ECM algorithm: a general framework. Biometrika 80:267–278MathSciNetCrossRefzbMATHGoogle Scholar
  28. Meng XL, van Dyk D (1997) The EM algorithm-an old folk-song sung to a fast new tune (with discussion). J R Stat Soc B 59:511–567CrossRefzbMATHGoogle Scholar
  29. Schwarz G (1978) Estimating the dimension of a model. Ann Stat 6:461–464MathSciNetCrossRefzbMATHGoogle Scholar
  30. Smirnov NV (1948) Tables for estimating the goodness of fit of empirical distributions. Ann Math Stat 19:279–281MathSciNetCrossRefzbMATHGoogle Scholar
  31. Wang WL, Lin TI (2013) An efficient ECM algorithm for maximum likelihood estimation in mixtures of \(t\)-factor analyzers. Comput Stat 28:751–769MathSciNetCrossRefzbMATHGoogle Scholar
  32. Wu CFJ (1983) On the convergence properties of the EM algorithm. Ann Stat 11:95–103MathSciNetCrossRefzbMATHGoogle Scholar
  33. Wu LC (2014) Variable selection in joint location and scale models of the skew-\(t\)-normal distribution. Commun Stat Simul Comput 43:615–630MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  • Mostafa Tamandi
    • 1
  • Ahad Jamalizadeh
    • 1
  • Tsung-I Lin
    • 2
    • 3
    Email author
  1. 1.Department of Statistics, Faculty of Mathematics & ComputerShahid Bahonar University of KermanKermanIran
  2. 2.Institute of StatisticsNational Chung Hsing UniversityTaichungTaiwan
  3. 3.Department of Public HealthChina Medical UniversityTaichungTaiwan

Personalised recommendations