Nonlinear Financial Econometrics: Markov Switching Models, Persistence and Nonlinear Cointegration

This book proposes new methods to value equity and model the Markowitz efficient frontier using Markov switching models. In particular, the book proposes that there are substantial differences between 'bull' and 'bear' market efficient portfolios that need to be taken into account when building diversified portfolios. Also, the book proposes a new concept of persistence that may be used to define and better understand the concept of nonlinear cointegration. In addition, the book reviews the recent developments of using fractional integrated models to model stock market volatility and suggests a new explanation for the persistence observed in share prices and their associated returns. Lastly, the book develops a new procedure that involves using the bootstrap to build vector error correction models and as an application, investigates the nonlinear relationship between oil and stock markets, respectively