OLS Asymptotics for Vector Autoregressions with Deterministic Regressors

Mynbayev, Kairat (2007): OLS Asymptotics for Vector Autoregressions with Deterministic Regressors. Published in: EURASIAN MATHEMATICAL JOURNAL , Vol. 9, No. 1 (2018): pp. 40-68.

Abstract

We consider a mixed vector autoregressive model with deterministic exogenous regressors and an autoregressive matrix that has characteristic roots inside the unit circle. The errors are (2+\epsilon)-integrable martingale differences with heterogeneous second-order conditional moments. The behavior of the ordinary least squares (OLS) estimator depends on the rate of growth of the exogenous regressors. For bounded or slowly growing regressors we prove asymptotic normality. In case of quickly growing regressors (e.g., polynomial trends) the result is negative: the OLS asymptotics cannot be derived using the conventional scheme and any diagonal normalizer.

• Item Type: MPRA Paper
• Language: English
• Keywords: time-series regression, asymptotic distribution, OLS estimator, polynomial trend, deterministic regressor
• Subjects: C - Mathematical and Quantitative Methods > C0 - General > C00 - General; C - Mathematical and Quantitative Methods > C0 - General > C01 - Econometrics; C - Mathematical and Quantitative Methods > C3 - Multiple or Simultaneous Equation Models ; Multiple Variables > C32 - Time-Series Models ; Dynamic Quantile Regressions ; Dynamic Treatment Effect Models ; Diffusion Processes ; State Space Models

References

[1] T.W. Anderson, The Statistical Analysis of Time Series, Wiley & Sons, 1971. [2] T. Amemiya, Advanced Econometrics, Oxford, Blackwell, 1985. [3] T.W. Anderson, N. Kunitomo, Asymptotic distribution of regression and autoregression coefficients with martingale difference disturbances, J. Multivariate Anal. 40 (1992), 221–243. [4] T.W. Anderson, N. Kunitomo, Asymptotic robustness of tests of overidentification and predeterminedness, J. Econometrics. 62 (1994), 383–414. [5] D.W.K. Andrews, Laws of large numbers for dependent non-identically distributed random variables, Economet. Theory. 4 (1988), 458–467. [6] D.W.K. Andrews, C.J. McDermott, Nonlinear econometric models with deterministically trending variables, Rev. Econ. Stud. 62 (1995), 343–360. [7] N.H. Bingham, C.M. Goldie, J.L. Teugels, Regular Variation, Cambridge University Press, 1987. [8] D.L. Burkholder, Distribution function inequalities for martingales, Ann. Prob. 1 (1973), 14–42. [9] W. Charemza, D.F. Deadman, New Directions in Econometric Practice: General to Specific Modelling, Cointegration, and Vector Autoregression, E. Elgar, 1992. [10] J. Davidson, Stochastic Limit Theory: An Introduction for Econometricians, Oxford University Press, 1994. [11] A. Dvoretzky, Asymptotic normality for sums of dependent variables, Proceedings of the Sixth Berkeley Symposium in Mathematical Statistics and Probability, University of California Press, 1972, 513–555. [12] F.R. Gantmacher, Matrizentheorie, VEB Deutscher Verlag der Wissenschaften, 1986. [13] P. Hall, C.C. Heyde, Martingale Limit Theory and Its Application, Academic Press, 1980. [14] J.D. Hamilton, Time Series Analysis, Princeton University Press, 1994. [15] T.-H. Kim, S. Pfaffenzeller, T. Rayher, P. Newbold, Testing for linear trend with applications to relative commodity prices, J. Time Ser. Anal. 24 (2003), 539–551. [16] H. L¨utkepohl, Introduction to Multiple Time Series Analysis, Springer-Verlag, 1991. [17] K.T. Mynbaev, Lp-approximable sequences of vectors and limit distribution of quadratic forms of random variables, Adv. Appl. Math. 26 (2001), 302–329. [18] K.T. Mynbaev, Asymptotic properties of OLS estimates in autoregressions with bounded or slowly growing deterministic trends, Commun. Stat. Theory. 35 (2006), 499–520. [19] K.T. Mynbaev, Short-memory linear processes and econometric applications, Wiley & Sons, 2011. [20] K.T. Mynbaev, Central limit theorems for weighted sums of linear processes: Lp-approximability versus Brownian motion, Economet. Theory, 25 (2009), 748-763. [21] K.T. Mynbaev, A. Ullah, Asymptotic distribution of the OLS estimator for a purely autoregressive spatial model, J. Multivariate Anal. 99 (2008), 245–277. [22] K.T. Mynbaev, Asymptotic distribution of the OLS estimator for a mixed regressive, spatial autoregressive model, J. Multivariate Anal. 101 (2010), 733–748. [23] K.T. Mynbaev, I. Castelar, The Strengths and Weaknesses of L2-approximable Regressors. Two Essays on Econometrics, Fortaleza: Express˜ao Gr´afica. 1, 2001. http://mpra.ub.uni-muenchen.de/9056/ [24] B. Nielsen, Strong consistency results for Least Squares estimators in general vector autoregressions with deterministic terms, Economet. Theory. 21 (2005), 534–561. [25] P.C.B. Phillips, Regression with slowly varying regressors and nonlinear trends, Economet. Theory. 23 (2007), 557-614. [26] B.M. P¨otscher, I.R. Prucha, Basic structure of the asymptotic theory in dynamic nonlinear econometric models, Part I: Consistency and approximation concepts, Econometric Rev. 10 (1991), 125–216. [27] C.A. Sims, J.H. Stock, M.W. Watson, Inference in linear time series models with some unit roots, Econometrica. 58 (1990), 113–144. [28] K. Tanaka, Time Series Analysis: Nonstationary and Noninvertible Distribution Theory, Wiley & Sons, 1996.