Search results

This chapter estimates a regime switching Taylor Rule for the European Central Bank (ECB) in order to investigate some potential nonlinearities in the forward-looking policy reaction function within a real-time framework. In order to compare observed and predicted policy behavior, the chapter estimates Actual and Perceived regime switching Taylor Rules for the ECB. The former is based on the refi rate set by the Governing Council while the latter relies on the professional point forecasts of the refi rate performed by a large investment bank before the upcoming policy rate decision. The empirical evidence shows that the Central Bank’s main policy rate has switched between two regimes: in the first one the Taylor Principle is satisfied and the ECB stabilizes the economic outlook, while in the second regime the Central Bank cuts rates more aggressively and puts a higher emphasis on stabilizing real output growth expectations. Second, the results point out that the professional forecasters have broadly well predicted the actual policy regimes. The estimation results are also robust to using consensus forecasts of inflation and real output growth. The empirical evidence from the augmented Taylor Rules shows that the Central Bank has most likely not responded to the growth rates of M3 and the nominal effective exchange rate and the estimated regimes are robust to including these additional variables in the regressions. Finally, after the bankruptcy of Lehman Brothers the policy rate has switched to a crisis regime as the ECB has focused on preventing a further decline in economic activity and on securing the stability of the financial system.

We address an interesting case – the predictability of excess US asset returns from macroeconomic factors within a flexible regime-switching VAR framework – in which the presence of regimes may lead to superior forecasting performance from forecast combinations. After documenting that forecast combinations provide gains in predictive accuracy and that these gains are statistically significant, we show that forecast combinations may substantially improve portfolio selection. We find that the best-performing forecast combinations are those that either avoid estimating the pooling weights or that minimize the need for estimation. In practice, we report that the best-performing combination schemes are based on the principle of relative past forecasting performance. The economic gains from combining forecasts in portfolio management applications appear to be large, stable over time, and robust to the introduction of realistic transaction costs.

We compare the finite sample power of short- and long-horizon tests in nonlinear predictive regression models of regime switching between bull and bear markets, allowing for time varying transition probabilities. As a point of reference, we also provide a similar comparison in a linear predictive regression model without regime switching. Overall, our results do not support the contention of higher power in longer horizon tests in either the linear or nonlinear regime switching models. Nonetheless, it is possible that other plausible nonlinear models provide stronger justification for long-horizon tests.

Using a market model of international equity returns, which fully incorporates the regime switching and heteroskedasticity effects, we conduct an empirical study on the asymmetric behavior of 31 emerging equity markets across the different regimes of both the global and the local markets. Asymmetric correlation is found to be much weaker than that among developed markets as documented in the recent studies. There is little evidence of performance enhancement by possessing information on asymmetric correlation in international asset allocation strategies involving emerging markets.

Real estate investment has been generally accepted as a value-adding proposition for a portfolio investor. Such an impression is not only shared by investment professionals and financial advisors but also appears to be supported by an overwhelming amount of research in the academic literature. The benefits of adding real estate as an asset class to a well-diversified portfolio are usually attributed to the respectable risk-return profile of real estate investment together with the relatively low correlation between its returns and the returns of other financial assets. By using the regime-switching technique on an extensive historical dataset, we attempt to look for the statistical evidence for such a claim. Unfortunately, the empirical support for the claim is neither strong nor universal. We find that any statistically significant improvement in risk-adjusted return is very much limited to the bullish environment of the real estate market. In general, the diversification benefit is not found to be statistically significant unless investors are relatively risk averse. We also document a regime-switching behavior of real estate returns similar to those found in other financial assets. There are two distinct states of the real estate market. The low-return (high-return) state is characterized by its high (low) volatility and its high (low) correlations with the stock market returns. We find this kind of dynamic risk characteristics to play a crucial role in dictating the diversification benefit from real estate investment.

Introduction: Studies on the insurance sector/companies have, in recent years, taken their place in literature at an increasing rate. Especially after the 2008 global financial crisis, the need for people to ensure their assets has structurally changed both the transaction volume and the yield structure of insurance sector. The increase in demand for insurance has also increased the appetite of investors to make an investment on this sector. The transaction volume of the insurance sector has increased year by year coupled with the number of insurance companies traded on the stock exchanges has started to increase in the same direction.

Aim: This chapter aims to determine the return structure of the Borsa Istanbul Insurance Index (XSGRT) based on daily closing values.

Method: Markedly with similar studies in the literature review, the authors determined that the Markov Regime Switching (MRS) model is the best-suited model for the current research. It was applied for the data set of XSGRT Index from 1997 to 2020.

Results: The result shows that XSGRT has three regimes named as expansion regime, normal regime and recession regime. Subsequently, it has been determined that the index generally attends to transition from the recession regime to the expansion regime and normal regime. This outcome is statistically significant at a 5% significance level and confirmed by backtesting results. Likewise, the duration of the recession regime is longer than the normal and expansion regime.

Conclusion: Despite the fact that the XSGRT has not yet completed its development compared to other main and sectoral indices, it is one of the indices that offer attractive earnings for investors. To put it differently, the desire of insurance companies to stay longer totally in the normal and expansion period and their immediate exit from the recession period provides them with a significant competitive advantage in contrast to other indices.

Originality/Value: This research contributes to the literature by providing additional evidence for existing studies using the longer duration of data set and applying the MRS model for Insurance Index. Best of our knowledge, it is the first study that examines the return structure of XSGRT based on its daily closing values from 1997 to 2020. In essence, investors can use the result of this study and compare it with other stock indices to make the accurate investment decision to maximise their welfare and return on their equity investments. The authors suggest that not only the return but also the regime structures of the invested shares (indices) should be taken into account for investment decisions.

The authors introduce a new approach to estimate high-dimensional factor-augmented vector autoregressive models (FAVAR) where the loadings are subject to idiosyncratic regime-switching dynamics. Our Bayesian estimation method alleviates computational challenges and makes the estimation of high-dimensional FAVAR with heterogeneous regime-switching straightforward to implement. The authors perform extensive simulation experiments to study the finite sample performance of our estimation method, demonstrating its relevance in high-dimensional settings. Next, the authors illustrate the performance of the proposed framework for studying the impact of credit market disruptions on a large set of macroeconomic variables. The results of this study underline the importance of accounting for non-linearities in factor loadings when evaluating the propagation of aggregate shocks.

The purpose of this study is to contrast the forecasting performance of two non-linear models, a regime-switching vector autoregressive model (RS-VAR) and a recurrent neural network (RNN), to that of a linear benchmark VAR model. Our specific forecasting experiment is U.K. inflation and we utilize monthly data from 1969 to 2003. The RS-VAR and the RNN perform approximately on par over both monthly and annual forecast horizons. Both non-linear models perform significantly better than the VAR model.