Exchange rate volatility, corruption, and economic growth

This study assesses the impact of exchange rate volatility on economic growth using a panel of 194 countries for the period 1995-2019. We resort to dynamic panel data models considering the exchange rate volatility estimated based on GARCH models as an explanatory variable, along with some control variables such as the level of economic openness and financial development, investment, government spending, and the expected level of education. Countries are grouped according to the level of corruption of the governments. The estimates from both Difference and System Generalized Method of Moments are obtained. The results consistently show a significant negative effect of exchange rate volatility on economic growth, which diminishes as the financial system develops. An important finding is that the effect of volatility is lower in high-corruption countries, which could be because they are used to dealing with the economic instability associated with low levels of governance and incorporate it as part of their costs.

Stock market volatility from the Covid-19 pandemic: New evidence from the Asia-Pacific region

Responses from stock markets to the Covid-19 pandemic appear to change over time. Recent responses might differ as herd mentality in stock markets tends to become herd immunity to the pandemic. This study revisits the pandemic's effects on the Asia-Pacific countries' market volatility over the past 25 months. Primarily, we examine the changes of the impacts of the pandemic on volatility between the first pandemic period (2020) and the second period (January 2021–January 2022). Our findings indicate that implementing pandemic control measures helps reduce market volatility at the country and region levels. The effects of new Covid-19 cases and pandemic control measures on market volatility have been dramatically fading since 2021. The Toda-Yamamoto causality test and the panel impulse response functions from panel VAR estimation are also used for robustness analysis. Based on our findings, it appears that the current pandemic may no longer be blamed for stock market volatility in the Asia-Pacific region.

Optimal forecasting accuracy using Lp-norm combination

A well-known result in statistics is that a linear combination of two-point forecasts has a smaller Mean Square Error (MSE) than the two competing forecasts themselves (Bates and Granger in J Oper Res Soc 20(4):451-468, 1969). The only case in which no improvements are possible is when one of the single forecasts is already the optimal one in terms of MSE. The kinds of combination methods are various, ranging from the simple average (SA) to more robust methods such as the one based on median or Trimmed Average (TA) or Least Absolute Deviations or optimization techniques (Stock and Watson in J Forecast 23(6):405-430, 2004). Standard regression-based combination approaches may fail to get a realistic result if the forecasts show high collinearity in several situations or the data distribution is not Gaussian. Therefore, we propose a forecast combination method based on Lp-norm estimators. These estimators are based on the Generalized Error Distribution, which is a generalization of the Gaussian distribution, and they can be used to solve the cases of multicollinearity and non-Gaussianity. In order to demonstrate the potential of Lp-norms, we conducted a simulated and an empirical study, comparing its performance with other standard-regression combination approaches. We carried out the simulation study with different values of the autoregressive parameter, by alternating heteroskedasticity and homoskedasticity. On the other hand, the real data application is based on the daily Bitfinex historical series of bitcoins (2014-2020) and the 25 historical series relating to companies included in the Dow Jonson, were subsequently considered. We showed that, by combining different GARCH and the ARIMA models, assuming both Gaussian and non-Gaussian distributions, the Lp-norm scheme improves the forecasting accuracy with respect to other regression-based combination procedures.