Textbook in PDF format

Testing for a Unit Root is now an essential part of time series analysis but the literature on the topic is so large that knowing where to start is difficult even for the specialist. This book provides a way into the techniques of unit root testing, explaining the pitfalls and nonstandard cases, using practical examples and simulation analysis. Front Matter Some Common Themes Functional Form and Nonparametric Tests for a Unit Root Fractional Integration Semi-Parametric Estimation of the Long-memory Parameter Smooth Transition Nonlinear Models Threshold Autoregressions Structural Breaks in AR Models Structural Breaks with Unknown Break Dates Conditional Heteroscedasticity and Unit Root Tests Back Matter