Model Uncertainty and Exchange Rate Forecasting

Kouwenberg, Roy; Markiewicz, Agnieszka; Verhoeks, Ralph; Zwinkels, Remco C. J.

doi:10.1017/s0022109017000011

Cited by 30 publications

(18 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Along these lines, this kind of disagreement in forecasting measures is not uncommon and has also been documented for exchange rates (see, e.g., Abbate & Marcellino, ; Fratzscher, Rime, Sarno, & Zinna, ). An exception in this respect is Kouwenberg et al (), who report successful results also in terms of point forecasting accuracy, though at a quarterly data frequency over a different evaluation period and exchange rates/fundamentals different from ours. We report results for our sample based on their approach in the Supporting Information Appendix.…”

Section: Resultscontrasting

confidence: 66%

“…Other techniques have been successfully used, including elastic net shrinkage (Li, Tsiakas, & Wang, ), gradient boosting (Berge, ), and model averaging/selection (Della Corte, Sarno, & Tsiakas, ; Della Corte & Tsiakas, ; Kouwenberg, Markiewicz, Verhoeks, & Zwinkels, ). All these approaches find sparsity to be an important modeling feature and, in particular, Kouwenberg et al () illustrate also the time‐varying relevance of regressors in a univariate framework. Our work corroborates these findings in a multivariate approach that allows us to assess the incremental value of fundamentals in addition to VAR lags and vice versa.…”

Section: Relation To the Literaturementioning

confidence: 99%

“…The literature has also explored the implications of exchange rate predictability (or a lack thereof) for an investor wishing to build an investment portfolio involving various exchange rates; see, for instance, Abhyankar, Sarno, and Valente (), Della Corte et al (), Kouwenberg et al (), and Abbate and Marcellino ().…”

Section: Relation To the Literaturementioning

confidence: 99%

See 2 more Smart Citations

Exchange rate predictability and dynamic Bayesian learning

Beckmann

Koop

Korobilis

et al. 2020

J of Applied Econometrics

View full text Add to dashboard Cite

We consider how an investor in the foreign exchange market can exploit predictive information by means of flexible Bayesian inference. Using a variety of vector autoregressive models, the investor is able, each period, to learn about important data features. The developed methodology synthesizes a wide array of established approaches for modeling exchange rate dynamics. In a thorough investigation of monthly exchange rate predictability for 10 countries, we find that using the proposed methodology for dynamic asset allocation achieves substantial economic gains out of sample. In particular, we find evidence for sparsity, fast model switching, and exploitation of the exchange rate cross-section.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Section: Resultscontrasting

confidence: 66%

Section: Relation To the Literaturementioning

confidence: 99%

See 1 more Smart Citation

Exchange rate predictability and dynamic Bayesian learning

Beckmann

Koop

Korobilis

et al. 2020

J of Applied Econometrics

View full text Add to dashboard Cite

show abstract

“…It is worth noting the use of simulation, though on the basis of the training method of support vectors (Yuan, 2013) as well as to improve the quality of the forecast using random processes (Moosa, 2013). Attention is drawn to the account of uncertainty in the forecasting of exchange rates (Kouwenberg, Markiewicz, Verhoeks, 2017;Detken C. 2002). It is proposed to use cointegration methods and random processes models (Moosa, Vaz, 2016) including those that take into account incomplete information (Juselius, 2017).…”

Section: Introductionmentioning

confidence: 99%

Simulation-based forecasting of the real effective exchange rate of the ruble

Vorontsovsky¹,

Vyunenko²

2019

Proceedings of the Third International Economic Symposium (IES 2018)

View full text Add to dashboard Cite

The real exchange rate of national currency is known to be one of the most important macroeconomic indicators. In this paper, we explore the opportunities of the Monte Carlo simulation technique combined with the polynomial residuals model for a medium-term forecasting the index of the real effective exchange rate for the ruble. The idea of the proposed approach is based on the successive (variable) differences method, designed for smoothing time series characterized by trend component and irregular component. The approach is illustrated numerically with the simulation-based forecast for the ruble real effective exchange rate, the values of the index in September-December 2017 being used to assess the forecast quality. The parameters in the corresponding polynomial residues models were calculated using the Nelder-Mead algorithm. The results of simulations at different "estimate depth" values and MAPE and RSME values indicate that the proposed approach allows constructing a relatively accurate medium-term forecast for the ruble effective exchange rate.

show abstract

“…Other topics of study include: the impact of exchange rates on prospects for economic growth [Dosse, 2007;Eichengreen, 2007]; exchange rates under conditions of open economy models, given global prices for raw materials [Manzur, 2018], including oil [Volkov, Yuhn, 2016]; predicting dynamics of exchange rate indices using ARMA models [Rout et al, 2014], including continuous ARMA models [Arratia, Cabana A., Cabana E., 2016] and GARCH models with modifications [Gupta, Kashyap, 2016;Barunik, Krehlik, Vacha, 2016]; applying neural networks for forecasting exchange rates [Liu, Hou, Liu, 2017;Zhenhua, Zezheng, Chao, 2016]; using the Support Vector Machine method and genetic algorithms to forecast daily exchange rates [Özorhan, Toroslu, Sehitoglu, 2017] or including panel data analysis, taking into account macroeconomic indicators and market volatility [Morales-Arias, Moura, 2013]. Some scholars draw attention to uncertainty in forecasting exchange rates [Kouwenberg, Markiewicz, Verhoeks, 2017;Detken, 2002], while others propose using cointegration methods and random processes models [Moosa, Vaz, 2016] predict exchange rates, including models taking into account incomplete information [Juselius, 2017]. It is worth noting the use of simulation, based on the Support Vector Machine method [Yuan, 2013] to improve the quality of forecasts based on random processes [Moosa, 2013].…”

Section: Introductionmentioning

confidence: 99%

Analyzing dynamics and forecasting real effective exchange rates for BRICS countries (1994–2016)

Shavshukov

Vorontsovsky

Vyunenko³

2018

SUJES

View full text Add to dashboard Cite

This article analyses the behavior of real effective exchange rates of BRICS countries and Eurocurrencies (USD & GBP). The obtained data reveals regularities in the behavior of BRICS currencies during the period of 1994-2016 and confirms that rates in the export-focused economy depend on the structure of the international market of real and financial assets. It also demonstrates high currency volatility (on average 50 % in the group) in the zone reaching the level of BIS real effective exchange rate (REER) = 100 (CPI-base 2010). The fundamental analysis shows that in the long-term , BRICS currencies demonstrate stable growth and the fixed rate regime (as Yuan) proved to be the most efficient in the formation of the national segment of global economy. Downward trends in Forex reflect debut difficulties BRICS economies and finances experienced in the process of integration into the global financial and economic environment. High turbulence and volatility of the REER in the range of 60-130 % was the result of the global crisis of 2008-2009 and oil shocks in 2014-2015. The REER below 100 % reflects low corporate and global competitiveness of BRICS economies and weaknesses in public and corporate finance, not the stability of currencies. This research provides a long-term forecast for the strengthening of currencies, as a result of growing efficiency of national economies and the creation of BRICS financial infrastructure (New Development Bank [capital $100 bln] and Pool Contingent Reserve Arrangement [startup capital $100 bln]), as well as an increase in the share of national currencies in mutual payments. The possibility for constructing a short-term forecast, based on the polynomial residues model and statistical modeling, is demonstrated in the case of BRICS currencies. The results of the short-term BIS REER forecast can also be used for forecasting the behavior of currencies, hedging by participants of foreign trade transactions, and currency policy of central banks.

show abstract

Model Uncertainty and Exchange Rate Forecasting

Cited by 30 publications

References 47 publications

Exchange rate predictability and dynamic Bayesian learning

Exchange rate predictability and dynamic Bayesian learning

Simulation-based forecasting of the real effective exchange rate of the ruble

Analyzing dynamics and forecasting real effective exchange rates for BRICS countries (1994–2016)

Contact Info

Product

Resources

About