On winning forecasting competitions in economics

To explain which methods might win forecasting competitions on economic time series, we consider forecasting in an evolving economy subject to structural breaks, using mis-specified, data-based models. ‘Causal’ models need not win when facing deterministic shifts, a primary factor underlying systematic forecast failure. We derive conditional forecast biases and unconditional (asymptotic) variances to show that when the forecast evaluation sample includes sub-periods following breaks, non-causal models will outperform at short horizons. This suggests using techniques which avoid systematic forecasting errors, including improved intercept corrections. An application to a small monetary model of the UK illustrates the theory.     

‘Time-series’ versus ‘econometric’ forecasts : A non-linear regression counterexample

A non-linear regression model is presented in which a deterministic, model-based forecast of the dependent variable may have greater mean square error than a purely extrapolative forecast, in contrast to the result on relative forecast efficiency in linear models.     

风电场风速预测的不确定性研究

风速预测的超前性导致其预测结果是不确定的,传统的确定性风速预测只提供确切的数值,不能满足电网规划的要求。分析了风速预测结果不确定性影响因素,并在确定性预测结果的基础上,从条件概率和预测误差分布统计规律两个角度对预测概率和置信区间进行分析和计算。仿真试验表明该方法能够为决策者提供概率预测信息,具有一定的实用性和有效性。     

IMPROVING FORECAST ACCURACY BY COMBINING RECURSIVE AND ROLLING FORECASTS*

This article presents analytical, Monte Carlo, and empirical evidence on combining recursive and rolling forecasts when linear predictive models are subject to structural change. Using a characterization of the bias–variance trade‐off faced when choosing between either the recursive and rolling schemes or a scalar convex combination of the two, we derive optimal observation windows and combining weights designed to minimize mean square forecast error. Monte Carlo experiments and several empirical examples indicate that combination can often provide improvements in forecast accuracy relative to forecasts made using the recursive scheme or the rolling scheme with a fixed window width.     

Spurious deterministic seasonality and autocorrelation corrections with quarterly data: Further Monte Carlo results

Following recent work of Franses, Hylleberg and Lee (FHL), this paper analyses the consequences of fitting a deterministic seasonal model to a quarterly time series which can be (at least approximately) described by a seasonal unit root(s) model. Besides the distribution of the coefficient of determination, the empirical distributions of two commonly used statistics are also investigated through Monte Carlo experiments for small, moderately large and large samples. FHL's work is also extended allowing the possibility of residual autocorrelation corrections. The main conclusion that emerges from the results is that one should not try to measure the importance of deterministic seasonality nor test for its presence in the context of such (static) regression models, even when using some form of residual autocorrelation correction. A simple empirical application is provided to illustrate our results. First version received: July 1997/final version received: July 1998     

Forecasting volatility in the Chinese stock market under model uncertainty

Volatility forecasting is an important issue in empirical finance. In this paper, the main purpose is to apply the model averaging techniques to reduce volatility model uncertainty and improve volatility forecasting. Six GARCH-type models are considered as candidate models for model averaging. As to the Chinese stock market, the largest emerging market in the world, the empirical study shows that forecast combination using model averaging can be a better approach than the individual forecasts.     

Forecasting Irregularly Spaced UHF Financial Data: Realized Volatility vs UHF-GARCH Models

A new literature has been recently devoted to the modeling of ultra-high-frequency (UHF) data. Our first aim is to develop an empirical application of UHF-GARCH models to forecast future volatilities on irregularly spaced data. We also compare the out-sample performance of these generalized autoregressive conditional heteroskedastic (GARCH) models with the realized volatility method. We propose a procedure to account for the time deformation problem and show how to use these models for computing daily Value at Risk (VaR).     

Purchasing power parity over two centuries: trends and nonlinearity

In two recent contributions Lothian and Taylor, and Cuddington and Liang, produced empirical evidence that annual data for the dollar-sterling real exchange rate spanning two centuries exhibited a non-linear deterministic trend. This trend could be proxying Harrod-Balassa-Samuelson effects. Lothian and Taylor showed that a linear stationary autoregressive mode, which embodied a cubic trend, implied much faster mean reversion of the real exchange rate to shocks than a model that excluded the trend. This article shows that both non-linearity and a deterministic trend can be allowed for in a theoretically appealing manner and that the fitted models provide a parsimonious explanation of both the dollar-sterling and franc-sterling real exchange rates over the two centuries of data. Generalized impulse response function analysis of the models demonstrates that the speed of adjustment to shocks can be even faster when trends are considered.     

Understanding and forecasting aggregate and disaggregate price dynamics

There are doubts regarding the empirical benefits of forecast aggregation. Theoretical research clearly supports forecast aggregation but conflicting results exist in the empirical literature. We search the literature for empirical regularities. One important issue often cited is estimation error and papers which are unsupportive of forecast aggregation often have short spans of data. A second empirical regularity is that researchers frequently use a relatively small number of disaggregates. Our work finds that the greatest benefits to aggregation are realised when a large number of disaggregates are used. This is a natural consequence of the theoretical results. A second critical issue in forecast aggregation is model selection. We suggest a simple guide to model choice based on the empirical properties of the data. In this regard, the extent of comovements between the constituent series determines model choice.     

Innovation forecasting

Technological forecasting is premised on a certain orderliness of the innovation process. Myriad studies of technological substitution, diffusion, and transfer processes have yielded conceptual models of what matters for successful innovation, but most technological forecasts key on limited empirical measures quite divorced from those innovation process models. We glean a number of concepts from various innovation models, then present an array of bibliometric measures that offer the promise of operationalizing these concepts. Judicious combination of such bibliometrics with other forms of evidence offers an enriched form of technological forecasting we call “innovation forecasting.” This provides a good means to combine technological trends, mapping of technological interdependencies, and competitive intelligence to produce a viable forecast. We illustrate by assessing prospects for ceramic engine technologies.     

Rational expectations and M2 demand

This essay expands on existing studies of M2 money demand. It differs in that it applies a rational expectations approach to an adaptive expectation model. Unlike the adaptive expectations models, the author includes an explanatory variable for expectations of future inflation. The expectation variables used are: the actual inflation rate (t + 1) and the Livingston Survey from the Philadelphia Fed. By using the different measures of expectations the author is able to compare several adaptive expectations models that appear in the literature and the rational expectations models for fit and forecast ability. The empirical results are such that the importance of including the rational expectations variable is evident even though the overall fit of the equation is comparable to one of the existing adaptive expectations models.     

S&P500 volatility analysis using high-frequency multipower variation volatility proxies

The availability of ultra-high-frequency data has sparked enormous parametric and nonparametric volatility estimators in financial time series analysis. However, some high-frequency volatility estimators are suffering from biasness issues due to the abrupt jumps and microstructure effect that often observed in nowadays global financial markets. Hence, we motivate our studies with two long-memory time series models using various high-frequency multipower variation volatility proxies. The forecast evaluations are illustrated using the S&P500 data over the period from year 2008 to 2013. Our empirical studies found that higher-power variation volatility proxies provide better in-sample and out-of-sample performances as compared to the widely used realized volatility and fractionally integrated ARCH models. Finally, these empirical findings are used to estimate the one-day-ahead value-at-risk of S&P500.     

Empirical Regularities of Financial Market Volatility and Good Modelling Process: Developing Countries’ Exchange Rate Markets Perspective

A survey of contemporary literature suggests that empirical studies on developing economies are few or almost non-existent. Engle and Patton (2001, What good is a volatility model. Quantitative Finance, 1, 237–245) as well as Poon (2005, A Practical Guide to Forecasting Financial Market Volatility. New Jersey: Wiley.) suggest that a good volatility model is one that utilizes the empirical regularities of financial market volatility (of which most were observed on industrialized economies markets). This paper uses exchange rate series from Ghana, Mozambique and Tanzania to show that;

1. they are not different from other financial markets as they exhibit most of the empirical regularities including volatility sign asymmetry, non-normal distribution and volatility clustering. It is however observed that the three exchange rate series are very volatile, with induced volatile shocks highly persistent and asymmetric, and extreme prices commonplace;

2. the ARCH technique (which has been well documented to capture these empirical regularities and produce good forecasts) generally produced a good fit to the three exchange rate series when compared with volatility forecasts generated using the EWMA technique. In the simple analysis of a day-ahead volatility forecast abilities of estimated models, it was observed that best fit does not necessarily ensure best forecast.

     

Volatility forecasting: combinations of realized volatility measures and forecasting models

This article examines financial time series volatility forecasting performance. Different from other studies which either focus on combining individual realized measures or combining forecasting models, we consider both. Specifically, we construct nine important individual realized measures and consider combinations including the mean, the median and the geometric means as well as an optimal combination. We also apply a simple AR(1) model, an SV model with contemporaneous dependence, an HAR model and three linear combinations of these models. Using the robust forecasting evaluation measures including RMSE and QLIKE, our empirical evidence from both equity market indices and exchange rates suggests that combinations of both volatility measures and forecasting models improve the forecast performance significantly.     

Monitoring and forecasting annual public deficit every month: the case of France

In this paper we forecast annual budget deficits using monthly information. Using French monthly data on central government revenues and expenditures, the method we propose consists of: (1) estimating monthly ARIMA models for all items of central government revenues and expenditures; (2) inferring the annual ARIMA models from the monthly models; (3) using the inferred annual ARIMA models to perform one-step-ahead forecasts for each item; (4) compounding the annual forecasts of all revenues and expenditures to obtain an annual budget deficit forecast. The major empirical benefit of this technique is that as soon as new monthly data become available, annual deficit forecasts are updated. This allows us to detect in advance possible slippages in central government finances. For years 2002–2004, forecasts obtained following the proposed approach are compared with a benchmark method and with official predictions published by the French government. An evaluation of their relative performance is provided.      

How do oil price forecast errors impact inflation forecast errors? An empirical analysis from US,French and UK inflation forecasts

This paper proposes an empirical investigation of the impact of oil price forecast errors on inflation forecast errors for three different sets of recent forecast data: the median of SPF inflation forecasts for the United States and the Central Bank inflation forecasts for France and the United Kingdom. Mainly two salient points emerge from our results. First, there is a significant contribution of oil price forecast errors to the explanation of inflation forecast errors, whatever the country or the period considered. Second, the pass-through of oil price forecast errors to inflation forecast errors is typically multiplied by around 2 when the oil price volatility is large.     

Understanding forecast failure of ESTAR models of real exchange rates

The forecast performance of the empirical ESTAR model of Taylor et al. (2001) is examined for 4 bilateral real exchange rate series over an out-of-sample evaluation period of nearly 12?years. Point as well as density forecasts are constructed, considering forecast horizons of 1 to 22 steps head. The study finds that no forecast gains over a simple AR(1) specification exist at any of the forecast horizons that are considered, regardless of whether point or density forecasts are utilised in the evaluation. Non-parametric methods are used in conjunction with simulation techniques to learn about the models and their forecasts. It is shown graphically that the nonlinearity in the conditional means (or point forecasts) of the ESTAR model decreases as the forecast horizon increases. The non-parametric methods show also that the multiple steps ahead forecast densities are normal looking with no signs of bi-modality, skewness or kurtosis.     

上证180指数的GARCH族模型仿真研究——对上证300指数的间接实证建模分析

本文旨在运用GARCH族模型对即将作为股指期货标的物——上证300指数进行间接实证建模研究。本文使用上证180指数研究上证300指数具有可行性。分析结果表明:上海股市股价波动确实存在显著的GARCH效应和冲击持久效应,并存在较弱的杠杆效应;收益率条件方差序列是平稳的,模型具有可预测性,GARCH-M(1,1)模型可以很好地拟合与预测上证180指数。该仿真模型可以较好地实现点对点的长期高精度预测,克服了传统预测模型只能进行短期预测的缺陷。这不仅对于投资者规避风险,开拓利润空间,而且对于我国资本市场的稳健发展,都具有重要的理论与实践指导意义。     

Volatility forecasting: long memory,regime switching and heteroscedasticity

In this article, we account for the first time for long memory, regime switching and the conditional time-varying volatility of volatility (heteroscedasticity) to model and forecast market volatility using the heterogeneous autoregressive model of realized volatility (HAR-RV) and its extensions. We present several interesting and notable findings. First, existing models exhibit significant nonlinearity and clustering, which provide empirical evidence on the benefit of introducing regime switching and heteroscedasticity. Second, out-of-sample results indicate that combining regime switching and heteroscedasticity can substantially improve predictive power from a statistical viewpoint. More specifically, our proposed models generally exhibit higher forecasting accuracy. Third, these results are widely consistent across a variety of robustness tests such as different forecasting windows, forecasting models, realized measures, and stock markets. Consequently, this study sheds new light on forecasting future volatility.     

Nonlinear exchange rate dynamics under stochastic official intervention

Many studies employ non-linear models to explain or forecast the exchange rate and find their superiority. This article builds an exchange rate model of managed float under conditional official intervention. In the model, the government minimizes social loss through a trade-off between targeting the exchange rate and lowering intervention costs. We obtain an endogenous threshold model and derive an analytical solution of the exchange rate stochastic interventions. The implication of a managed float causing a lower volatility of the exchange rate has been found by past empirical studies. Our model provides not only a justification for the central banks' conditional interventions but also a rationale for the use of regime-switching models of two states (intervention vs. non-intervention) in the empirical studies of exchange rates.