Abstract
Multiple linear regression model based on normally distributed and uncorrelated errors is a popular statistical tool with application in various fields. But these assumptions of normality and no serial correlation are hardly met in real life. Hence, this study considers the linear regression time series model for series with outliers and autocorrelated errors. These autocorrelated errors are represented by a covariance-stationary autoregressive process where the independent innovations are driven by shape mixture of skew-t normal distribution. The shape mixture of skew-t normal distribution is a flexible extension of the skew-t normal with an additional shape parameter that controls skewness and kurtosis. With this error model, stochastic modeling of multiple outliers is possible with an adaptive robust maximum likelihood estimation of all the parameters. An Expectation Conditional Maximization Either algorithm is developed to carryout the maximum likelihood estimation. We derive asymptotic standard errors of the estimators through an information-based approximation. The performance of the estimation procedure developed is evaluated through Monte Carlo simulations and real life data analysis.
Similar content being viewed by others
References
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 267–281
Anderson RL (1954) The problem of autocorrelation in regression analysis. J Am Stat Assoc 49(265):113–129
Barnett V, Lewis T (1995) Outliers in statistical data, 3rd edn. Wiley, New York
Bayrak OT, Akkaya AD (2010) Estimating parameters of a multiple autoregressive model by the modified maximum likelihood method. J Comput Appl Math 233(8):1763–1772
Beach CM, Mackinnon JG (1978) A maximum likelihood procedure for regression with autocorrelated errors. Econometrica 46(1):51–58
Cochrane D, Orcutt GH (1949) Application of least regression to relationships containing autocorrelated error terms. J Am Stat Assoc 44(245):32–61
Cramér H (1946) Mathematical methods of statistics. Princeton University Press, Princeton
Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data via the EM algorithm (with discussion). J R Stat Soc B 39:1–38
Durbin J (1960) Estimation of parameters in time-series regression models. J R Stat Soc Ser B (Methodol) 22(1):139–153
Efron B, Hinkley DV (1978) Assessing the accuracy of the maximum likelihood estimator: observed versus expected Fisher information. Biometrika 65:457–482
Gervini D, Yohai VJ (2002) A class of robust and fully efficient regression estimators. Ann Stat 30(2):583–616
Hamilton JD (1994) Time series analysis. Princeton University Press, New Jersey
Hogg RV (1974) Adaptive robust procedures: a partial review and some suggestions for future applications and theory. J Am Stat Assoc 69:909–923
Hu H (2013) Asymptotic normality of huber-dutter estimators in a linear model with AR(1) processes. J Stat Plan Inference 143(3):548–562
Huber PJ (1973) Robust regression: asymptotics, conjectures and Monte Carlo. Ann Stat 1(5):799–821
Huber PJ (1981) Robust statistics. Wiley, Hoboken
Koch KR (1999) Parameter estimation and hypothesis testing in linear models. Springer, Berlin
Lange KL, Little RJA, Taylor JMG (1989) Robust statistical modeling using the t distribution. J Am Stat Assoc 84:881–896
Little RJA, Rubin DB (2002) Statistical analysis with missing data, 2nd edn. Wiley, Hoboken
Liu CH (1997) ML estimation of the multivariate t distribution and the EM algorithm. J Multivar Anal 63:296–312
Liu CH, Rubin DB (1994) The ECME algorithm: a simple extension of EM and ECM with faster monotone convergence. Biometrika 81:633–648
Liu CH, Rubin DB (1995) ML estimation of the t distribution using EM and its extensions, ECM and ECME. Stat Sin 5:19–39
McDonald JB (1989) Partially adaptive estimation of ARMA time series models. Int J Forecast 5:217–230
McLachlan GJ, Krishnan T (2008) The EM algorithm and extensions, 2nd edn. Wiley, Hoboken
Meng X-L, Rubin DB (1993) Maximum likelihood estimation via the ECM algorithm: a general framework. Biometrika 80:267–278
Nadarajah S (2007) Explicit expressions for the moments of t order statistics. Comptes Rendus De Academie Science Paris,Series I 345(9):523–526
Nduka UC, Iwueze IS, Nwogu EC (2020) Efficient algorithms for robust estimation in autoregressive regression models using Student’s t distribution. Commun Stat Theory Methods 49(2):355–374
Priestley MB (1981) Spectral analysis and time series. Academic Press, Cambridge
Rousseeuw PJ (1984) Least median of squares regression. J Am Stat Assoc 79(388):871–880
Rousseeuw PJ (1985) Multivariate estimation with high breakdown point. Math Stat Appl 8(37):283–297
Rousseeuw PJ, Yohai VJ (1984) Robust regression by means of S-estimators
Schwarz G (1978) Estimating the dimension of a model. Ann Stat 6:461–464
Tamandi M, Jamalizadeh A, Lin T (2019) Shape mixtures of skew-t-normal distributions: characterizations and estimation. Comput Stat 34:323–347
Tiku ML, Wong W, Bian G (1999) Estimating parameters in autoregressive models in nonnormal situations: symmetric innovations. Commun Stat Theory Methods 28(2):315–341
Tuaç Y, Güney Y, Şenoğlu B, Arslan O (2018) Robust parameter estimation of regression model with AR (p) error terms. Commun Stat Simul Comput 47(8):2343–2359
Tuaç Y, Güney Y, Arslan O (2020) Parameter estimation of regression model with AR(p) error terms based on skew distributions with EM algorithm. Soft Comput 24:3309–3330
Wang WL, Lin TI (2013) An efficient ECM algorithm for maximum likelihood estimation in mixtures of t-factor analyzers. Comput Stat 28:751–769
Wong W, Bian G (2005) Estimating parameters in autoregressive models with asymmetric innovations. Stat Probab Lett 71(1):61–70
Wu CFJ (1983) On the convergence properties of the EM algorithm. Ann Stat 11:95–103
Yohai VJ (1987) High breakdown-point and high efficiency robust estimates for regression. Ann Stat 15(2):642–656
Yu C, Yao W (2017) Robust linear regression: A review and comparison. Commun Stat Simul Comput 46(8):6261–6282
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Nduka, U.C. Efficient and robust estimation for autoregressive regression models using shape mixtures of skewt normal distribution. Methodol Comput Appl Probab 24, 1519–1551 (2022). https://doi.org/10.1007/s11009-021-09872-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11009-021-09872-8
Keywords
- Autoregressive process
- Expectation maximization algorithm
- Linear regression model
- Robust estimation
- Skew-t-distribution