Incorporating economic policy uncertainty in US equity premium models: A nonlinear predictability analysis

Abstract

Information on economic policy uncertainty does matter in predicting the US equity premium, especially when accounting for structural instabilities and omitted nonlinearities in their relationship, via a quantile predictive regression approach over the monthly period 1900:1-2014:2. Unlike as suggested by a linear mean-based predictive model, the extended quantile regression model with the incorporation of the EPU proxy, enhances significantly the out-of-sample stock return predictability. This is observed especially when the market is neutral, exhibits a side or mildly upward trending behavior, yet not when the market appears to turn highly bullish.

The role of economic policy uncertainties in predicting stock returns and their volatility for Hong Kong, Malaysia and South Korea

“…In this regard, some mixed, primarily in-sample, international empirical evidence can be found in Antonakakis et al, (2013), Kang and Ratti (2013), Gupta et al, (2014), Bekiros, Gupta and Majumdar (2016), Brogaard and Detzel (2015), Chang et al, (2015), Chuliá et al, (2015), Jurado et al, (2015), Kang and Ratti (2015), Redl (2015), Bekiros, Gupta and Kyei (2016), Li et al, (2016), and Sum (2012c). All these above studies have related the own-country uncertainty with own-country stock returns.…”

The role of partisan conflict in forecasting the U.S. equity premium: A nonparametric approach

“…6 Based on the suggestions of an anonymous referee, we conducted various robustness checks. First, we used the interest rate on the year government bond as a measure of the risk-free rate; second, we used the economic policy uncertainty index as used in Bekiros et al, (2016), instead of the PCI; and third, we carried out a forecasting analysis based on the Vector Autoregressive (VAR) used by Cheng et al, (2016). We found that, i.e., irrespective of the measure of the risk-free rate, excess return is only predictable by PCI based on the FCAR model.…”

“…When the PCI is replaced by the EPU, the superiority of the FCAR model continues to hold. Finally, the Based on the suggestion of an anonymous referee, we also estimated the quantile predictive regression as in Bekiros et al, (2016), which in turn, provide an alternative approach to capture the nonlinear relationship between excess returns and the PCI. The results have been reported in Table 2.…”

“…As discussed in detail in Manela and Moreira (forthcoming), recent theoretical frameworks have emphasized time variation in rare event risk as a source of aggregate asset price fluctuations, which in turn, implies a link between partisan conflict and the equity market. In addition, as shown by Cheng et al, (2016) PCI leads to business cycle fluctuations, and given that, asset returns are functions of the state variables of the real economy, fluctuations in it due to partisan conflict is likely to affect the stock market via movements in real activity (Bekiros et al, 2016).…”

“…Traditionally, studies dealing with stock returns and equity premium prediction have used a linear predictive regression framework. However, recent contributions to the literature have pointed out that the relationship between returns and predictors is not linear (Bekiros et al, 2016). Given this, the literature has resorted to Markov-switching, smooth transition threshold, neural networks, non-or semi-parametric, time-varying coefficient and quantile models (Rapach and Zhou, 2013).…”