Chapter 46 UNIT ROOTS, STRUCTURAL JAMES H. STOCK Basic concepts The functional Examples central asymptotic limit theorem results theory and related tools and notation and preliminary. Generalizations and additional references | Chapter 46 UNIT ROOTS STRUCTURAL BREAKS AND TRENDS JAMES H. STOCK Harvard University Contents Abstract 2740 1. Introduction 2740 2. Models and preliminary asymptotic theory 2744 . Basic concepts and notation 2745 . The functional central limit theorem and related tools 2748 . Examples and preliminary results 2751 . Generalizations and additional references 2756 3. Unit autoregressive roots 2757 . Point estimation 2758 . Hypothesis tests 2763 . Interval estimation 2785 4. Unit moving average roots 2788 . Point estimation 2790 . Hypothesis tests 2792 5. Structural breaks and broken trends 2805 . Breaks in coefficients in time series regression 2807 . Trend breaks and tests for autoregressive unit roots 2817 6. Tests of the 1 1 and 1 0 hypotheses links and practical limitations 2821 . Parallels between the 1 0 and 1 1 testing problems 2821 . Decision-theoretic classification schemes 2822 . Practical and theoretical limitations in the ability to distinguish 1 0 and 1 1 processes 2825 References 2831 The author thanks Robert Amano Donald Andrews Jushan Bai Ngai Hang Chan In Choi David Dickey Frank Diebold Robert Engle Neil Ericsson Alastair Hall James Hamilton Andrew Harvey Sastry Pantula Pierre Perron Peter Phillips Thomas Rothenberg Pentti Saikkonen Peter Schmidt Neil Shephard and Mark Watson for helpful discussions and or coments on a draft of this chapter. Graham Elliott provided outstanding research assistance. This research was supported in part by the National Science Foundation Grants SES-89-10601 and SES-91-22463 . Handbook of Econometrics Volume IV Edited by . Engle and . McFadden 1994 Elsevier Science . All rights reserved 2740 . Stock Abstract This chapter reviews inference about large autoregressive or moving average roots in univariate time series and structural change in multivariate time series regression. The problem of unit roots is cast more broadly as determining the order of integration of a .
