Non‐linearities,Business Cycles and Exchange Rates

This paper conjoins the disparate empirical literatures on exchange rate models and monetary policy models, with special reference to the importance of output, inflation gaps and exchange rate targets. It focuses in on the dollar/euro exchange rate, and the differential results arising from using alternative measures of the output gap for the US and for the Euro area. A comparison of ‘in‐sample’ prediction against alternative models of exchange rates is also conducted. In addition to predictive power, I also assess the various models' plausibility as economic explanations for exchange rate movements, based on the conformity of coefficient estimates with priors. Taylor rule fundamentals appear to do as well, or better, than other models at the 1‐year horizon.     

A Note on Forecasting Emerging Market Exchange Rates: Evidence of Anti‐herding

Using survey forecasts of a large number of Asian, European, and South American emerging market exchange rates, we studied empirically whether evidence of herding or anti‐herding behavior of exchange‐rate forecasters can be detected in the cross‐section of forecasts. Emerging market exchange‐rate forecasts are consistent with herding (anti‐herding) if forecasts are biased towards (away from) the consensus forecast. Our empirical findings provide strong evidence of anti‐herding of emerging market exchange‐rate forecasters.     

Determinants and Forecast of Price Level in India: a VAR Framework

The theoretical association of money supply and exchange rates with prices has been empirically established and shown to be dominant in explaining changes in price levels in India. However, post liberalisation, studies have shown price levels to be impacted by several other factors as also, weakened influence of the traditional factors established by theories. This study aims to find the determinants of price level for the period 1994–2008 using a Vector Autoregression model and test the predictive ability of the model. Our results show shorter and smaller impact of change in money supply and nominal effective exchange rate on price levels. Both money supply and nominal effective exchange rates are found to Granger-cause Consumer Price Index. But, impulse response functions show that the impact of shocks from money supply and nominal effective exchange rates on consumer prices peaks after two lags and is short-lived. Forecast error variance decomposition shows that these demand side factors contribute only 6 % of the forecast error variation in Consumer Price Index.

     

Foreign Direct Investment in Australia Following the Australia–US Free Trade Agreement

A model of inward foreign direct investment for Australia is estimated. Foreign direct investment is found to be positively related to economic and productivity growth and negatively related to foreign portfolio investment, trade openness, the exchange rate and the foreign real interest rate. Foreign direct investment is found to be a substitute for both portfolio investment and trade in goods and services. The exchange rate and the US bond rate affect foreign direct investment through the relative attractiveness of domestic assets. Actual foreign direct investment outperforms a model‐derived forecast in recent years, consistent with the liberalisation of foreign investment screening rules following the Australia–US Free Trade Agreement.     

Dissecting models' forecasting performance

The fact that the predictive performance of models used in forecasting stock returns, exchange rates, and macroeconomic variables is not stable and varies over time has been widely documented in the forecasting literature. Under these circumstances excessive reliance on forecast evaluation metrics that ignores this instability in forecasting accuracy, like squared errors averaged over the whole forecast evaluation sample, masks important information regarding the temporal evolution of relative forecasting performance of competing models. In this paper we suggest an approach based on the combination of the Cumulated Sum of Squared Forecast Error Differential (CSSFED) of Welch and Goyal (2008) and the Bayesian change point analysis of Barry and Hartigan (1993) that tracks the contribution of forecast errors to the aggregate measures of forecast accuracy observation by observation. In doing so, it allows one to track the evolution of the relative forecasting performance over time. We illustrate the suggested approach by using forecasts of the GDP growth rate in Switzerland.     

Exchange rate exposure: Evidence from China

This paper examines exchange rate exposure using a sample of Chinese firms. To measure RMB exchange rate volatility and jump risk, we apply the autoregressive conditional jump intensity (ARJI) model to the industry‐specific nominal effective exchange rate (I‐NEER) for 13 Chinese manufacturing industries over the period 2001 to 2017, We find that exchange rate risks do affect firm value at the industry level, and the effect is more significant for the jump risks that are more difficult to hedge and in the sample period when hedge activities are less likely to occur. Our results suggest that the exposure puzzle could be a result of the endogeneity of operative and financial hedging. Firm‐level analysis finds that exchange rate risk affects firm value for more than 20% of Chinese firms, and a firm's exchange rate exposure varies with the firm's characteristics.     

SECULAR MEAN REVERSION AND LONG‐RUN PREDICTABILITY OF THE STOCK MARKET

The empirical financial literature reports evidence of mean reversion in stock prices and the absence of out‐of‐sample return predictability over horizons shorter than 10 years. Anecdotal evidence suggests the presence of mean reversion in stock prices and return predictability over horizons longer than 10 years, but thus far, there is no empirical evidence confirming such anecdotal evidence. The goal of this paper is to fill this gap in the literature. Specifically, using 141 years of data, this paper begins by performing formal tests of the random walk hypothesis in the prices of the real S&P Composite Index over increasing time horizons of up to 40 years. Although our results cannot support the conventional wisdom that the stock market is safer for long‐term investors, our findings speak in favor of the mean reversion hypothesis. In particular, we find statistically significant in‐sample evidence that past 15‐17 year returns are able to predict the future 15‐17 year returns. This finding is robust to the choice of data source, deflator, and test statistic. The paper continues by investigating the out‐of‐sample performance of long‐horizon return forecasting based on the mean‐reverting model. These latter tests demonstrate that the forecast accuracy provided by the mean‐reverting model is statistically significantly better than the forecast accuracy provided by the naive historical‐mean model. Moreover, we show that the predictive ability of the mean‐reverting model is economically significant and translates into substantial performance gains.     

HOW DO OIL PRICE SHOCKS AFFECT A SMALL NON‐OIL PRODUCING ECONOMY? EVIDENCE FROM HONG KONG

We find no evidence from either in‐sample or out‐of‐sample analyses that an oil price shock would necessarily affect a small non‐oil producing economy such as Hong Kong. In our in‐sample recursive vector autoregressive investigations, oil price does not Granger cause the key macroeconomic indicators. The forecast errors from our out‐of‐sample examination using a vector error correction model with oil shocks, which represents an extension to previous studies, were found to be statistically the same as those from the vector error correction model without these shocks. The analysis leads us to dispel the conventional wisdom that a small non‐oil producing economy is more vulnerable to oil shocks than a larger oil‐producing economy such as the USA.     

Monetary Shocks and Real Exchange Rate Dynamics: a Reappraisal

This paper proposes a two‐country general‐equilibrium model incorporating a tradable sector with pricing‐to‐market as well as a nontradable sector. In that case, real exchange rate fluctuations arise from two sources: changes in the relative price of traded goods, that exemplify deviations from the law of one price, and movements in the relative price of traded to nontraded goods across countries. Our framework sheds light on the propagation mechanisms through which monetary shocks affect the real exchange rate. More specifically, the two components respond in opposite directions to monetary disturbances, which is consistent with data. Besides, the introduction of nontraded goods does not alter the predictive power of monetary shocks because the presence of nontraded goods magnifies the response of the deviation from the law of one price.     

A new multiscale decomposition ensemble approach for forecasting exchange rates

Due to the high complexity and strong nonlinearity nature of foreign exchange rates, how to forecast foreign exchange rate accurately is regarded as a challenging research topic. Therefore, developing highly accurate forecasting method is of great significance to investors and policy makers. A new multiscale decomposition ensemble approach to forecast foreign exchange rates is proposed in this paper. In the approach, the variational mode decomposition (VMD) method is utilized to divide foreign exchange rates into a finite number of subcomponents; the support vector neural network (SVNN) technique is used to model and forecast each subcomponent respectively; another SVNN technique is utilized to integrate the forecasting results of each subcomponent to generate the final forecast results. To verify the superiority of the proposed approach, four major exchange rates were chosen for model comparison and evaluation. The experimental results indicate that our proposed VMD-SVNN-SVNN multiscale decomposition ensemble approach outperforms some other benchmarks in terms of forecasting accuracy and statistical tests. This demonstrates that our proposed VMD-SVNN-SVNN multiscale decomposition ensemble approach is promising for forecasting foreign exchange rates.     

The Taylor Rule,Wealth Effects and the Exchange Rate

In this study, we develop the Taylor rule and Taylor rule‐based exchange rate models that consider wealth effects as represented by both asset prices and asset wealth. Using data for Australia, Sweden, the UK and the USA, we find that effects of asset prices and wealth on the Taylor rule vary depending on the country and on the form that wealth takes. Out‐of‐sample forecasting capacities of the wealth‐augmented Taylor rule model and Taylor rule‐based exchange rate model outperform conventional models and random walk theories for these countries.     

Asymmetric effect of exchange rate volatility on India's cross‐border trade: Evidence from global financial crisis and multiple threshold nonlinear autoregressive distributed lag model

This paper examines the asymmetric effect of exchange rate volatility on India's cross‐border trade with its major trading partners: Japan, Germany, the United States, and China. We extend previous studies in two ways. First, we examine whether global financial crisis changes the asymmetric effect of exchange rate volatility on India's cross‐border trade. Next, we divide exchange rate volatility into quintiles and examine the effect of each quintile on cross‐border trade by using the multiple threshold nonlinear autoregressive distributed lag (MTNARDL) model. Our findings from standard nonlinear ARDL (NARDL) indicate that the asymmetric relationship between exchange rate volatility and cross‐border trade changes as a result of global financial crisis. In addition, findings from MTNARDL indicate that in short‐run, exchange rate volatility symmetrically affects India's cross‐border trade with all sample countries whereas in long‐run it asymmetrically affects cross‐border trade. Overall, these findings are very important for policy implications and open a new dimension to exchange rate volatility and trade flows.     

EXPLORING THE USEFULNESS OF A NONRANDOM HOLDOUT SAMPLE FOR MODEL VALIDATION: WELFARE EFFECTS ON FEMALE BEHAVIOR*

A particularly challenging use of decision‐theoretic models in economics is to forecast the impact of large changes in the environment. The problem we explore in this article is how to gain confidence in a model's ability to predict the impact of such large changes. We show that an approach to validation and model selection that includes the choice of a “nonrandom holdout sample,” a sample that differs significantly from the estimation sample along the policy dimension that the model is meant to forecast, can be fruitful.     

On the cross-sectional relation between exchange rates and future fundamentals

Using a cross-sectional perspective, we investigate the implications of the present-value model of exchange rates for a sample of 64 countries during 1971–2015, excluding periods of pegged exchange rates. Our paper uses all bilateral exchange rate pairs instead of choosing a reference currency and extends the list of fundamentals that have been examined in the previous literature by using the variables present in the behavioral equilibrium exchange rate (BEER) model. We document that exchange rates are strongly connected to future fundamentals using forecast horizons from one month to 10 years. Our findings highlight that unlike for time-series and panel data, the evidence against the “exchange rate disconnect puzzle” is more robust using a cross-sectional perspective. Given the relevance of fundamental factors in determining exchange rates dynamics we examine whether they are useful in constructing profitable investment strategies. Except for inflation, we find that a significant relation between exchange rates and a fundamental does not lead necessarily to a profitable investment strategy. Finally, we document that using the cross-rates of exchange rates leads to a significant improvement in the profitability of the carry trade strategy.     

ON THE SOURCES OF UNCERTAINTY IN EXCHANGE RATE PREDICTABILITY

In a unified framework, we examine four sources of uncertainty in exchange rate forecasting models: (i) random variations in the data, (ii) estimation uncertainty, (iii) uncertainty about the degree of time variation in coefficients, and (iv) uncertainty regarding the choice of the predictor. We find that models that embed a high degree of coefficient variability yield forecast improvements at horizons beyond one month. At the one‐month horizon, and apart from the standard variance implied by unpredictable fluctuations in the data, the second and third sources of uncertainty listed above are key obstructions to predictive ability. The uncertainty regarding the choice of the predictors is negligible.     

Forecasting and combining competing models of exchange rate determination

This article investigates the out-of-sample forecast performance of a set of competing models of exchange rate determination. We compare standard linear models with models that characterize the relationship between exchange rate and the underlying fundamentals by nonlinear dynamics. Linear models tend to outperform at short forecast horizons especially when deviations from long-term equilibrium are small. In contrast, nonlinear models with more elaborate mean-reverting components dominate at longer horizons especially when deviations from long-term equilibrium are large. The results also suggest that combining different forecasting procedures generally produces more accurate forecasts than can be attained from a single model.     

Forecasting volatility in the Indian equity market using return and range-based models

In this article, we assess the time-varying volatility of the National Stock Exchange in the Indian equity market using unconditional estimators and asymmetric conditional econometric models. The volatility estimate and forecast is computed from the interday return and intraday range-based data of the exchange’s flagship index, CNX NIFTY, for the time period spanning 1 January 2009 through 31 December 2013. These are our findings: First, we determine that the time-varying volatility of the index is asymmetric with qualities of stationarity and leptokurtic distribution. Second, the one-step-ahead volatility forecast derived from the univariate time series parameters through the GJR-GARCH ?????process indicates that the model evaluation criteria of the autoregressive process tends towards range-based models vis-à-vis a return-based model. The validity of this methodology is further analysed with the superior predictive ability test, the outcome of which supports the use of range-based conditional models. Finally, among the evaluated range-based model variants, the model confidence set procedure favours the Yang–Zhang estimator as being better suited to forecast the exchange’s volatility than the ones by Parkinson, Garman–Klass and Rogers–Satchell.     

A comparative study of exchange rates and order flow based on wavelet transform coherence and cross wavelet transform

Understanding the relationship and behavior of microstructures and exchange rates is an essential discussion for global foreign exchange investors. There are numerous research works regarding the linkage between order flow and exchange rates, yet the exact relationship between the order flow and the market price that indicates whether participants have an impact on the market trend remains undefined. This paper investigates the empirical association and behavior of order flow and the exchange rate movements within the time-frequency space, on three popular currency pairs, using the cross wavelet transform and wavelet transform coherency. The results indicate that order flow has a strong negative correlation and is the leader variable of the exchange rate. A predictor using order flow as an input variable was implemented to forecast the exchange rate direction using the sample data and out-of-sample data. This methodology, which performs with high accuracy and very low drawdown, could be a suitable tool for portfolio managers and forex participants during their trading activities.     

FORECASTING GLOBAL EQUITY INDICES USING LARGE BAYESIAN VARS

This paper proposes a large Bayesian Vector Autoregressive (BVAR) model with common stochastic volatility to forecast global equity indices. Using a monthly dataset on global stock indices, the BVAR model controls for co‐movement commonly observed in global stock markets. Moreover, the time‐varying specification of the covariance structure accounts for sudden shifts in the level of volatility. In an out‐of‐sample forecasting application we show that the BVAR model with stochastic volatility significantly outperforms the random walk both in terms of point as well as density predictions. The BVAR model without stochastic volatility, on the other hand, shows some merits relative to the random walk for forecast horizons greater than six months ahead. In a portfolio allocation exercise we moreover provide evidence that it is possible to use the forecasts obtained from our model with common stochastic volatility to set up simple investment strategies. Our results indicate that these simple investment schemes outperform a naive buy‐and‐hold strategy.     

A DSGE-VAR model for forecasting key South African macroeconomic variables

The paper develops a Small Open Economy New Keynesian DSGE-VAR (SOENKDSGE-VAR) model of the South African economy, characterised by incomplete pass-through of exchange rate changes, external habit formation, partial indexation of domestic prices and wages to past inflation, and staggered price and wage setting. The model is estimated using Bayesian techniques on data from the period 1980Q1 to 2003Q2, and then used to forecast output, inflation and nominal short-term interest rate for one-to eight-quarters-ahead over an out-of sample horizon of 2003Q3 to 2010Q4. When the forecast performance of the SOENKDSGE-VAR model is compared with an independently estimated DSGE model, the classical VAR and six alternative BVAR models, we find that, barring the BVAR model based on the SSVS prior on both VAR coefficients and the error covariance, the SOENKDSGE-VAR model is found to perform competitively, if not, better than all the other VAR models.