Switching-regime regression for modeling and predicting a stock market return
- PDF / 789,564 Bytes
- 19 Pages / 439.37 x 666.142 pts Page_size
- 68 Downloads / 180 Views
Switching-regime regression for modeling and predicting a stock market return Kenneth R. Szulczyk1 · Changyong Zhang2 Received: 2 February 2017 / Accepted: 29 July 2019 © Springer-Verlag GmbH Germany, part of Springer Nature 2019
Abstract It has been observed that certain economic and financial variables commonly exhibit switching behavior depending on their magnitude. This phenomenon in general cannot be naturally captured by the linear regression (LR), which assumes a linear relationship between the dependent and explanatory variables. To decipher investor behavior more appropriately by accounting for this observation, a switching-regime regression (SRR) is proposed and applied to the S&P 500 market return with respect to seven explanatory variables. It is shown that, compared with LR, the new regression results in a significantly improved adjusted R 2 , increasing from less than 4% to over 50%. In addition, SRR yields better out-of-sample forecasting performance, besides that the fitted values from the new regression even resemble the dip during the 2008 financial crisis, while those from LR do not. The study thus indicates that the switching-regime regression improves significantly the statistical properties including the goodness of fit as well as conforms more to investor behavior theory. Keywords Switching behavior · Linear regression · Threshold regression · Switching-regime regression · Goodness-of-fit · Out-of-sample forecasting JEL Classification C51 · C52 · C53 · E44 · G17 · G41
The authors gratefully thank the anonymous referee for carefully reviewing the earlier versions of the paper and providing valuable comments and suggestions, which helped to improve the paper significantly. The authors would also like to express their gratitude to Professor Robert Kunst for all the communications and comments in the process of handling the paper.
B
Changyong Zhang [email protected] Kenneth R. Szulczyk [email protected]
1
School of Economics and Management, Xiamen University Malaysia, Sepang, Malaysia
2
Department of Finance and Banking, Faculty of Business, Curtin University, Miri, Malaysia
123
K. R. Szulczyk, C. Zhang
1 Introduction In economics and finance, a regime indicates a particular state of an economy or market or signals a structural change. Switching behavior, which means a parameter in a regression depends on the magnitude or regime of a variable, has been commonly identified for economic and financial variables such as the exchange rates (Kräger and Kugler 1993), gross domestic product (Beaudry and Koop 1993), interest rates (Pfann et al. 1996), petroleum prices (Hamilton 1996, 2003), stock market returns (Narayan 2006), transaction costs (Hansen 2011), and unemployment rate (Koop and Potter 1999). A simple example of switching behavior results from transaction and transportation costs, as illustrated in Fig. 1. First, suppose that there is no transportation cost as shown in Panel A. If P1 , the price in Market 1 exceeds P2 that in Market 2, i.e., P1 > P2 , then arb
Data Loading...
