A Comparison of Alternative Exchange Rate Forecasting Models*

This paper compares a number of structural and times-series models on the basis of their accuracy in forecasting the A ustralian-US dollar exchange rate out of sample. Purchasing power parity, forward exchange theory, static and dynamic specifications of both the flexible price and sticky price monetary models, and univariate ARIMA models are considered in the paper. Exchange rate forecasts are generated at horizons of one to four quarters. In contrast to overseas results which support the view that the exchange rate follows a random walk, several models in this study are found to generate forecasts superior to the random walk model.     

Policy analysis in real time using IMF's monetary model

We investigate to what extent estimated relationships of the IMF's monetary model and their policy implications are sample dependent. We observe that estimates of the model's key parameters and model-based measures of macroeconomic disequilibria are highly dependent on the data vintage employed. Changes in parameter estimates solely due to data revisions are found to be much smaller than those owing to parameter instability, possibly reflecting model misspecification. Moreover, instability in parameter estimates contributes to more uncertainty in assessments of macroeconomic disequilibria than data revisions. Analyses based on a version of the model in difference form are also found to be quite sensitive to the data vintage employed, although to a lesser extent than those based on the standard version of the model with variables in levels.     

Re‐vitalizing money demand in the Euro area. Still valid at the zero‐lower bound

The analysis of monetary developments has always been a cornerstone of the ECB's monetary analysis and, thus, of its overall monetary policy strategy. In this respect, money demand models provide a framework for explaining monetary developments and assessing price stability over the medium term. It is a well‐documented fact in the literature that, when interest rates are at the zero‐lower bound, the analysis of money stocks become even more important for monetary policy. Therefore, this paper re‐investigates the stability properties of M3 demand in the euro area in the light of the recent economic crisis. A cointegration analysis is performed over the sample period 1983 Q1 and 2015 Q1 and leads to a well‐identified model comprising real money balances, income, the long‐term interest rate and the own rate of M3 holdings. The specification appears to be robust against the Lucas critique of a policy dependent parameter regime, in the sense that no signs of breaks can be found when interest rates reach the zero‐lower bound. Furthermore, deviations of M3 from its equilibrium level do not point to substantial inflation pressure at the end of the sample. Excess liquidity models turn out to outperform the autoregressive benchmark, as they deliver more accurate CPI inflation forecasts, especially at the longer horizons. The inclusion of unconventional monetary policy measures does not contradict these findings.     

FORECASTING THE UK/US EXCHANGE RATE WITH DIVISIA MONETARY MODELS AND NEURAL NETWORKS

This paper compares the UK/US exchange rate forecasting performance of linear and nonlinear models based on monetary fundamentals, to a random walk (RW) model. Structural breaks are identified and taken into account. The exchange rate forecasting framework is also used for assessing the relative merits of the official Simple Sum and the weighted Divisia measures of money. Overall, there are four main findings. First, the majority of the models with fundamentals are able to beat the RW model in forecasting the UK/US exchange rate. Second, the most accurate forecasts of the UK/US exchange rate are obtained with a nonlinear model. Third, taking into account structural breaks reveals that the Divisia aggregate performs better than its Simple Sum counterpart. Finally, Divisia‐based models provide more accurate forecasts than Simple Sum‐based models provided they are constructed within a nonlinear framework.     

Learning stability in economies with heterogeneous agents

An economy exhibits structural heterogeneity when the forecasts of different agents have different effects on the determination of aggregate variables. We study the important case of economies in which agents' behavior depends on forecasts of aggregate variables and show how different forms of heterogeneity in structure, forecasts, and adaptive learning rules affect the conditions for convergence of adaptive learning towards rational expectations equilibrium. Results are applied to an overlapping generations model and a New Keynesian model of monetary policy.     

Financial market imperfections and monetary policy strategy

In a model with imperfect money, credit and reserve markets, we examine if an inflation-targeting central bank applying the funds rate operating procedure to indirectly control market interest rates also needs a monetary aggregate as policy instrument. We show that if private agents use information extracted from money and financial markets to form inflation expectations and if interest rate pass-through is incomplete, the central bank can use a narrow monetary aggregate and the discount interest rate as independent and complementary policy instruments to reinforce the credibility of its announcements and the role of inflation target as a nominal anchor for inflation expectations. This study shows how a monetary policy strategy combining inflation targeting and monetary targeting can be conceived to guarantee macroeconomic stability and the credibility of monetary policy. Friedman's k-percent money growth rule, which can generate dynamic instability, and two alternative stabilizing feedback monetary targeting rules are examined.     

Forecasting the barbados money supply

The purpose of this paper is to provide an adequate forecasting method for the money supply in the Barbadian economy. This would assist the Central Bank in making decisions on monetary intervention. The performance of ARIMA and vector autoregressive forecasting models are investigated along with combinations of these models. The results of this study suggest that there are reasonable options available for obtaining reliable forecasts of the Barbados money supply. Our findings indicate that seasonal factors and interest rate effects should be comprehended within the forecasting model. We accomplished this through a combination forecasting procedure in which seasonal effects are captured by an ARIMA model and interest rates are introduced through a vector autoregressive forecasting model as exogenous variables.     

Fixed exchange rate credibility with heterogeneous expectations

After disinflation has been achieved, agents who form more sophisticated forecasts have lower confidence in the sustainability of a peg compared to less sophisticated agents. Furthermore, sustained financial stability leads to a declining proportion of sophisticated agents. Thus, the credibility of a fixed exchange rate regime grows over time partly because fewer people pay attention to the workings of the monetary regime. These results are derived in a rules-versus-discretion model of a fixed exchange rate regime with heterogeneous agents. We provide unique supporting evidence using data on expectations and information about the monetary regime from Bulgaria’s currency board.     

Monetary Policy and Forecasts for Real GDP Growth: An Empirical Investigation for the Federal Republic of Germany

Using quarterly data for the Federal Republic of Germany, we generate four-quarter-ahead forecasts for real GDP growth. Throughout the 1970s and 1980s, other monetary indicators like real M1 or short-run interest rates clearly outperform forecasts which are based on interest rate spreads. This holds for within as well as for ex-post predictions. The same holds for the development after 1992. Moreover, it is shown that simple forecasts based on M1 or on short-run interest rates outperform the common biannual GNP forecasts of the group of German economic research institutes.     

A small-scale DSGE-VAR model for the Romanian economy

This paper describes the theoretical structure and the estimation results for a DSGE-VAR model for the Romanian economy, an inflation targeting country since 2005. Having as benchmark the New-Keynesian model of Rabanal and Rubio-Ramirez (2005), the main additional feature introduced refers to the extension to a small open economy setting in order to account for this specific aspect of the Romanian economy.Within the inflation targeting monetary policy regime, forecasts of central macro variables, inflation in particular, play an important part. Because inflation reacts to monetary measures with a considerable lag, the central bank's policy has to be forward-looking. Based on univariate measures of forecast performance, it is shown that the VAR with DSGE model prior produces forecasts that improve on those obtained using an unrestricted VAR model and the popular Minnesota prior in case of inflation, real exchange rate and nominal interest rate. Moreover, the DSGE-VAR model is informative about the structure of the economy and can help the “story-telling” in the central banks.     

Labour markets, liquidity, and monetary policy regimes

Abstract.  We develop an equilibrium model of the monetary policy transmission mechanism that highlights information frictions in the market for money and search frictions in the labour market. The information friction increases the persistence in the response of interest rates following monetary policy regime shifts. This occurs because agents have incomplete information about the nature of the shifts and optimally update their inflation forecasts using an 'adaptive' expectations rule. The search friction transmits the interest rate movements to the labour market by affecting job creation activities; together, the two frictions imply that unemployment reacts very gradually to monetary policy shocks. JEL Classification: E4, E5     

An adaptive approach to forecasting three key macroeconomic variables for transitional China

The macroeconomic forecasts for emerging economies often suffer from the constraints of instability and limited data. In light of these constraints, we propose the use of a local autoregressive (LAR) model with a data-driven estimation window, i.e., a local homogenous interval, that is adaptively identified to strike a balance between information efficiency and stability. When applied to three key macroeconomic variables of China, the LAR model substantially outperforms the alternative models for various forecast horizons of 3 to 12 months, with forecast error reductions of between 4% and 64% for the IP growth, and between 1% and 68% for the inflation rate. The one-quarter ahead performance of the LAR model matches that of a well-known survey forecast. The patterns of the identified local intervals also coincide with the characteristic evolution of the gradual reforms and monetary policy shifts in China. In short, the LAR model is suitable for not only forecasting, but also the real-time monitoring of the effects of regime and policy changes in emerging economies.     

DSGE model-based forecasting of modelled and nonmodelled inflation variables in South Africa

Inflation forecasts are a key ingredient for monetary policy-making – especially in an inflation targeting country such as South Africa. Generally, a typical Dynamic Stochastic General Equilibrium (DSGE) only includes a core set of variables. As such, other variables, for example alternative measures of inflation that might be of interest to policy-makers, do not feature in the model. Given this, we implement a closed-economy New Keynesian DSGE model-based procedure which includes variables that do not explicitly appear in the model. We estimate such a model using an in-sample covering 1971Q2 to 1999Q4 and generate recursive forecasts over 2000Q1 to 2011Q4. The hybrid DSGE performs extremely well in forecasting inflation variables (both core and nonmodelled) in comparison with forecasts reported by other models such as AR(1). In addition, based on ex-ante forecasts over the period 2012Q1–2013Q4, we find that the DSGE model performs better than the AR(1) counterpart in forecasting actual GDP deflator inflation.     

Short-Run and Long-Run Dynamics of Exchange Rates with Sticky Prices

This paper constructs microfoundations for the nexus between sticky goods prices and exchange rate overshooting. Based on an asset-pricing model, this paper describes how the exchange rate responds to a monetary shock in the short run and adjusts in later periods to a new long-run rate. In an environment where goods prices are sticky, the short-run response of the exchange rate to a monetary shock depends on the elasticity of consumption demand. The long-run exchange rate always shifts equiproportionately to a monetary shock regardless of the parameter values and is reached many periods after the shock.     

Money,Interest Rate and Foreign Exchange Rate As Indicator Variables Of Monetary Policy

Since monetary policy operations affect the ultimate targets such as real income and prices with considerable time lags, this papers attempts to identify the indicator variable of monetary policy in Korea by using autoregression tests, variance docompositions of VAR forecasts and cointegration analyses. The results show that in Korea unlike the U.S., a broad concept of money, interest rate and foreign exchange rate, taken together, could serve as the indicator variables. In particular, M3, But not M2 nor MCT, is significantly related to real income both in the short-run and in the long-run. Such a finding rejects the practice of controlling either M2 or MCT which the Korean monetary authority had exercised before implementing the recent IMF financial-reform program. [E5]     

通货膨胀目标区与非线性泰勒法则

本文采用STR、TV-STR模型,利用1991年1月至2010年3月的月度数据分析了我国货币政策反应函数,与现有中国货币政策反应函数的文献相比主要有以下几个结论:第一,我国货币政策反应函数存在着结构变化,先是在1997年11月突变,然后存在一个渐变过程.第二,1997年11月前后相应存在着两个通货膨胀目标区,分别为[14.109,16.123]和[0.985,2.902],且后一通货膨胀目标区要比前一通货膨胀目标区合理.第三,随着时间推移,我国货币政策反应函数的产出缺口反应系数,逐渐由负转正,利率平滑系数则逐渐变小,这反应了随着我国利率市场化的推进,我国的货币政策操作开始越来越多的使用利率这一价格工具.     

An Estimated DSGE Model for Business Cycle Analysis in China

A small-scale, but highly-stylized dynamic stochastic general equilibrium model is estimated by the maximum likelihood method using Chinese quarterly data. Model specifications and parameter equalities between various competing model variants are addressed by formal statistical hypothesis tests, while implications for business cycle fluctuations are evaluated via a variance decomposition experiment, second-moments matching, and some out-of-sample forecast exercises. It is highlighted that the monetary authority takes an aggressive stance to the current inflation pressure (there is a significant lagged response), while leaving less attention to changes in aggregate output. Variance decomposition reveals that large percentages of variations in real and nominal variables are explained by the highly volatile preference and potential output shock, respectively. When nominal and real frictions as well as additional shocks are included, overall our estimated model can successfully reproduce the stylized facts from actual data of Chinese business cycles and frequently can even outperform those forecasts from an unconstrained VAR.     

Detecting and Predicting Forecast Breakdowns

We propose a theoretical framework for assessing whether a forecast model estimated over one period can provide good forecasts over a subsequent period. We formalize this idea by defining a forecast breakdown as a situation in which the out-of-sample performance of the model, judged by some loss function, is significantly worse than its in-sample performance. Our framework, which is valid under general conditions, can be used not only to detect past forecast breakdowns but also to predict future ones. We show that main causes of forecast breakdowns are instabilities in the data-generating process and relate the properties of our forecast breakdown test to those of structural break tests. The empirical application finds evidence of a forecast breakdown in the Phillips' curve forecasts of U.S. inflation, and links it to inflation volatility and to changes in the monetary policy reaction function of the Fed.     

Taylor rules and the Great Inflation

Can US monetary policy in the 1970s be described by a stabilizing Taylor rule when policy is evaluated with real-time inflation and output gap data? Using economic research on the full employment level of unemployment and the natural rate of unemployment published between 1970 and 1977 to construct real-time output gap measures for periods of peak unemployment, we find that the Federal Reserve did not follow a Taylor rule if appropriate measures are used. We estimate Taylor rules and find no evidence that monetary policy stabilized inflation, even allowing for changes in the inflation target. While monetary policy was stabilizing with respect to inflation forecasts, the forecasts systematically under-predicted inflation following the 1970s recessions and this does not constitute evidence of stabilizing policy. We also find that the Federal Reserve responded too strongly to negative output gaps.     

Business Cycles in an Estimated DSGE Model of China

A small-scale New-Keynesian dynamic stochastic general equilibrium model is estimated by maximum likelihood method using quarterly data of China. Model specifications and parameter equalities between various competing model variants are addressed by formal statistical hypothesis tests, while implications for business cycle fluctuations are evaluated via a variance decomposition experiment, second-moments matching, and some out-of-sample forecast exercises. It is highlighted that both forward and backward components are important for the dynamics of output, inflation and real balances. The monetary authority will take a sufficient aggressive stance, with a significant lagged response, to the current inflation pressure, while leaving less attention to changes in aggregate output. Variance decomposition reveals that large percentages of variations in real and nominal variables are explained by the highly volatile preference shock and potential output shock, respectively. When nominal and real frictions as well as additional shocks are included, our estimated model overall can successfully reproduce the stylized facts of business cycles in the actual data of China and even frequently outperform those forecasts from an unconstrained VAR.