Robust autoregressive modeling and its diagnostic analytics with a COVID-19 related application

Autoregressive models in time series are useful in various areas. In this article, we propose a skew-t autoregressive model. We estimate its parameters using the expectation-maximization (EM) method and develop the influence methodology based on local perturbations for its validation. We obtain the normal curvatures for four perturbation strategies to identify influential observations, and then to assess their performance through Monte Carlo simulations. An example of financial data analysis is presented to study daily log-returns for Brent crude futures and investigate possible impact by the COVID-19 pandemic. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

[1]  Adelchi Azzalini,et al.  An overview on the progeny of the skew-normal family - A personal perspective , 2021, J. Multivar. Anal..

[2]  Gilberto A. Paula,et al.  Estimation and diagnostic for partially linear models with first-order autoregressive skew-normal errors , 2021, Comput. Stat..

[3]  Víctor Leiva,et al.  Asymmetric autoregressive models: statistical aspects and a financial application under COVID-19 pandemic , 2021, Journal of applied statistics.

[4]  Robert G. Aykroyd,et al.  A new BISARMA time series model for forecasting mortality using weather and particulate matter data , 2020 .

[5]  Manuel Galea,et al.  Birnbaum-Saunders Quantile Regression Models with Application to Spatial Data , 2020, Mathematics.

[6]  Víctor Leiva,et al.  Diagnostic Analytics for an Autoregressive Model under the Skew-Normal Distribution , 2020, Mathematics.

[7]  Lei Shi,et al.  Time Series Analysis Using SAS Enterprise Guide , 2020 .

[8]  V. Leiva,et al.  Birnbaum–Saunders functional regression models for spatial data , 2019, Stochastic Environmental Research and Risk Assessment.

[9]  M. Huerta,et al.  On a partial least squares regression model for asymmetric data with a chemical application in mining , 2019, Chemometrics and Intelligent Laboratory Systems.

[10]  V. Leiva,et al.  Sensitivity analysis of longitudinal count responses: a local influence approach and application to medical data , 2018, Journal of Applied Statistics.

[11]  Viviana Giampaoli,et al.  Influence diagnostics in mixed effects logistic regression models , 2018, TEST.

[12]  Helton Saulo,et al.  Incorporation of frailties into a cure rate regression model and its diagnostics and application to melanoma data , 2018, Statistics in medicine.

[13]  Víctor Leiva,et al.  Robust multivariate control charts based on Birnbaum–Saunders distributions , 2018 .

[14]  Shuangzhe Liu,et al.  Diagnostic analysis for a vector autoregressive model under Student′s t‐distributions , 2017 .

[15]  Lei Shi,et al.  Detection of outliers in mixed regressive-spatial autoregressive models , 2016 .

[16]  Shuangzhe Liu,et al.  Influence diagnostic analysis in the possibly heteroskedastic linear model with exact restrictions , 2015, Statistical Methods & Applications.

[17]  A. SenGupta,et al.  Influence Diagnostics in Possibly Asymmetric Circular-Linear Multivariate Regression Models , 2016, Sankhya B.

[18]  Fukang Zhu,et al.  Local influence analysis for Poisson autoregression with an application to stock transaction data , 2016 .

[19]  Shuangzhe Liu,et al.  Influence diagnostics in a vector autoregressive model , 2015 .

[20]  Víctor Leiva,et al.  Diagnostics in elliptical regression models with stochastic restrictions applied to econometrics , 2015 .

[21]  Fukang Zhu,et al.  Influence diagnostics in log-linear integer-valued GARCH models , 2015 .

[22]  Martin Eling,et al.  Fitting asset returns to skewed distributions: Are the skew-normal and skew-student good models? , 2014 .

[23]  J. Shi,et al.  Diagnostics on nonlinear model with scale mixtures of skew-normal and first-order autoregressive errors , 2014 .

[24]  Aldo M. Garay,et al.  Statistical diagnostics for nonlinear regression models based on scale mixtures of skew-normal distributions , 2014 .

[25]  B. Carmichael,et al.  Asset pricing with skewed-normal return , 2013 .

[26]  Fei Chen,et al.  Outlier Detection in Time Series Models Using Local Influence Method , 2012 .

[27]  V. H. Lachos,et al.  Local influence analysis for regression models with scale mixtures of skew-normal distributions , 2011 .

[28]  V. H. Lachos,et al.  A nonlinear regression model with skew-normal errors , 2010 .

[29]  R. Tsay.  Analysis of Financial Time Series: Tsay/Financial Time Series 3E , 2010 .

[30]  Tsung-I Lin,et al.  Robust linear mixed models using the skew t distribution with application to schizophrenia data , 2010, Biometrical journal. Biometrische Zeitschrift.

[31]  Feng-Chang Xie,et al.  Diagnostics for skew-normal nonlinear regression models with AR(1) errors , 2009, Comput. Stat. Data Anal..

[32]  Shuangzhe Liu,et al.  On pseudo maximum likelihood estimation for multivariate time series models with conditional heteroskedasticity , 2009, Math. Comput. Simul..

[33]  Gilberto A. Paula,et al.  Influence diagnostics for linear models with first-order autoregressive elliptical errors , 2009 .

[34]  C. Heyde,et al.  On estimation in conditional heteroskedastic time series models under non-normal distributions , 2008 .

[35]  Jack C. Lee,et al.  Robust mixture modeling using the skew t distribution , 2007, Stat. Comput..

[36]  T. Kollo,et al.  Advanced Multivariate Statistics with Matrices , 2005 .

[37]  A. Azzalini,et al.  Distributions generated by perturbation of symmetry with emphasis on a multivariate skew t‐distribution , 2003, 0911.2342.

[38]  H. Neudecker,et al.  Matrix Differential Calculus with Applications , 1988 .

[39]  Jorge I. Figueroa-Zúñiga,et al.  Matrix differential calculus with applications in the multivariate linear model and its diagnostics , 2022, J. Multivar. Anal..

[40]  Shuangzhe Liu,et al.  On diagnostics in conditionally heteroskedastic time series models under elliptical distributions , 2004, Journal of Applied Probability.

[41]  Yat Sun Poon,et al.  Conformal normal curvature and assessment of local influence , 1999 .