Estimation and Forecasting in Models with Multiple Breaks

This paper develops a new approach to change-point modelling that allows the number of change-points in the observed sample to be unknown. The model we develop assumes that regime durations have a Poisson distribution. It approximately nests the two most common approaches: the time-varying parameter (TVP) model with a change-point every period and the change-point model with a small number of regimes. We focus considerable attention on the construction of reasonable hierarchical priors both for regime durations and for the parameters that characterize each regime. A Markov chain Monte Carlo posterior sampler is constructed to estimate a version of our model, which allows for change in conditional means and variances. We show how real-time forecasting can be done in an efficient manner using sequential importance sampling. Our techniques are found to work well in an empirical exercise involving U.S. GDP growth and inflation. Empirical results suggest that the number of change-points is larger than previously estimated in these series and the implied model is similar to a TVP (with stochastic volatility) model.     

Time Series Dynamics of Sugar Export Earnings in Fiji with Multiple Endogenous Structural Breaks: Implications for EU Sugar and Industry Reforms

Journal of Quantitative Economics - The sugar industry has been the backbone of the Fijian economy since the late 1950s. Owing to its poor performance over the recent years, and especially the...     

Testing For and Dating Common Breaks in Multivariate Time Series

This paper develops methods for constructing asymptotically valid confidence intervals for the date of a single break in multivariate time series, including I(0) , I(1) , and deterministically trending regressors. Although the width of the asymptotic confidence interval does not decrease as the sample size increases, it is inversely related to the number of series which have a common break date, so there are substantial gains to multivariate inference about break dates. These methods are applied to two empirical examples: the mean growth rate of output in three European countries, and the mean growth rate of U.S. consumption, investment, and output.     

中国宏观经济时序的平稳性再考察——内生突变与平滑转换

对宏观变量是由确定性趋势所主导还是由随机趋势所主导的区分涉及预测精度以及潜在数据生成过程的认知理念等问题,本文意在指出若将结构变化包括在内单位根观念的认知需要扭转。具体地,文章用傅里叶级数拟合经济时序,与先前研究不同的是在处理突变方式上把对突变位置和突变方式的估计转化为恰当频率的选择问题。对中国15个代表性宏观时序的考察表明,视大多宏观变量为平滑转换的趋势平稳过程更为合适。     

20世纪90年代时间序列预测领域主要研究动态

20世纪90年代,预测领域取得了比较丰硕的研究成果.预测方法除主观判断方法外,主要有单变量方法和多变量方法.单变量方法在实际中使用最多,主要涉及分数差分模型、结构模型、贝叶斯预测方法.多元回归方法仍是最常用的多变量预测方法,但对经济时间序列拟合多元回归模型存在一些问题,于是人们对向量回归模型进行了大量的研究.本文着重分析了国外学者关于预测方法的选择以及非线性模型的研究动态.     

Structural Breaks,Biased Estimations,and Forecast Errors in a GDP Series of Canada versus the United States

International Advances in Economic Research - A structural break was suspected for the Canadian gross domestic product (GDP) time series when the reporting system switched from the Standard...     

Fuzzy Seasonal Time Series for Forecasting the Production Value of the Mechanical Industry in Taiwan

Based on the seasonal time series ARIMA(p,d,q)(P,D,Q)_s model (SARIMA) and fuzzy regression model, we combine the advantages of two methods to propose a procedure of fuzzy seasonal time series and apply this method to forecasting the production value of the mechanical industry in Taiwan. The intention of the article is to provide the enterprises, in this era of diversified management, with a fresh method to conduct short-term prediction for the future in the hope that these enterprises can perform more accurate planning. This method includes interval models with interval parameters and provides the possibility distribution of future value. From the results of practical application to the mechanical industry, it can be shown that this method makes good forecasts. Further, this method makes it possible for decision makers to forecast the possible situations based on fewer observations than the SARIMA model and has the basis of pre-procedure for fuzzy time series.     

Rethinking Long Memory and Structural Breaks in the Forward Premium

This paper documents new results that the ability of structural breaks to explain away non‐stationary long memory in the forward premium weakens considerably with higher‐frequency data. For daily data, removing structural breaks does not make non‐stationary long memory stationary, contrary to the evidence for monthly data reported in the recent literature. Simulating data on a daily basis, we show that using monthly data tends to overstate the importance of structural breaks, and obfuscate the true nature of persistence, in the forward premium. Our results thus corroborate earlier findings that long memory bears primary responsibility for the forward premium anomaly.     

Decentralization Effects in Ecological Fiscal Transfers: A Bayesian Structural Time Series Analysis for Portugal

Portugal has a unitary system in which the central government transfers funds to lower government levels for their public functions. In 2007, Portugal introduced Ecological Fiscal Transfers (EFT), where municipalities receive transfers for hosting protected areas (PA). We study whether introducing EFT in Portugal incentivized municipalities to designate PA and has led to a decentralization of conservation decisions. We employ a Bayesian structural time series approach to estimate the effect of introducing EFT in comparison to a simulated counterfactual time series. Quantitative results show a significant increase in the ratio of municipal and national PA designations following Portugal’s EFT introduction—which we infer to be a causal consequence. The analysis furthermore places emphasis on the importance of relevant municipal conservation competencies for the functioning of the instrument. Results have important implications for conservation policy-making in terms of allocating budgets and competencies in multi-level governments.     

Visualising Time: A Compendium of Time Series Plots

Graphs are important for highlighting relationships within a data series or across several series. Modern computer software has provided flexibility in the construction of graphic displays that would have been impossible with the tools that were available to researchers only a few decades ago. This article illustrates a variety of different graphical presentations for time ordered or time series data that can now be constructed. These include time series plots, bar charts, range plots, radar charts, scatter plots, heat maps and seasonality plots. For each graph type presented, we discuss the best practice for their construction.     

A Test of Long-run Purchasing Power Parity Allowing for Structural Breaks*

If exchange rates and prices are integrated processes, standard econometric tests of the purchasing power parity (PPP) hypothesis may be biased towards rejection. This paper avoids this problem by using the Engle and Granger (1987) theory of cointegrated processes. If the absolute version of purchasing power parity is true, and nominal exchange rates and prices are integrated processes, inter-commodity arbitrage should ensure that the real exchange rate is stationary. The stationarity hypothesis is tested using Australian real exchange rate data for the 1890–1984 period We find that the effective real exchange rate cannot be modelled as a stationary process and therefore reject the absolute version of PPP. We also employ a test for structural breaks due to, for instance, the oil price shock and find mixed results. Another interpretation of our results is that the real exchange rate was affected by a series of permanent, real shocks during the sample period     

基于结构突变理论的国内出游率趋势探析

通过考虑结构变化的单位根检验发现,1985～2008年的国内旅游年人均出游率是一个带有两个结构突变点的趋势平稳过程。1993年为截距突变点,2002年为截距与趋势双突变点。2003年后的出游率年均增长量远高于前期,以现有趋势看,可提前一年达到我国提出的2015年居民年均出游超过2次的发展目标。     

Price Discovery and Risk Transfer in the Crude Oil Futures Market: Some Structural Time Series Evidence

This paper re-examines the Garbade and Silber (1983) model with the objective of finding out if the crude oil futures market performs the functions of price discovery and risk transfer. The model is estimated, using daily data, as a system of two seemingly unrelated time series equations allowing the coefficients to be time-varying. The empirical results reveal that the futures market performs about 60 per cent of the price discovery function, and that the elasticity of supply of arbitrage services is adequately high for the market to perform the risk transfer function.
(J.E.L: G13, C22).     

计量经济学方法之时间序列分析

本文介绍了一元时间序列分析中常用的AR、MA、ARMA和ARIMA等经典模型,分析了这几个经典模型的理论要点以及单位根检验的方法和程序,总结了时间序列分析在预测等方面的优势及其在复杂科学管理中的应用,并以我国一月期国债回购利率和上证180月收益率为分析对象,介绍了一元线性回归分析的基本步骤。     

Time-Frequency Analysis for Nonstationary Time Series

Non-stationary time series are a frequently observed phenomenon in several applied fields, particularly physics, engineering and economics. The conventional way of analysing such series has been via stationarity inducing filters. This can interfere with the intrinsic features of the series and induce distortions in the spectrum. To avert this possibility, it might be a better alternative on occasions to proceed directly with the series via the so-called time-varying spectrum. This article outlines the circumstances under which such an approach is possible, drawing attention to the practical applicability of these methods. Several methods are discussed and their relative advantages and drawbacks delineated.

     

Value-at-Risk in the Presence of Structural Breaks Using Unbiased Extreme Value Volatility Estimator

Journal of Quantitative Economics - We provide a framework based on the unbiased extreme value volatility estimator to predict long and short position value-at-risk (VaR). The given framework...     

Some Basic Issues in Time Series Modelling

Journal of Quantitative Economics - The notion of individual freedom has been around in economics for a long time. The formal analysis of individual freedom in welfare economics, however, is of...     

季节时间序列理论发展综述

随着社会的进步,统计数据由过去的年度数据变为如今的季度、月度和日度数据,有些以实时交易为基础的超高频金融数据达到了按秒为间隔的频率,这些数据被称为季节时间序列。季节时间序列研究已经成为近十年来经济计量学和统计学中的热点,Joumal of Econometrics（1993,volume 55）就此问题进行了专题讨论。本文按照历史发展顺序对季节性时间序列理论进行了系统地介绍,并对这一领域的前沿热点问题进行了评述和展望。     

On the Instability of Tunisian Money Demand: Some Empirical Issues with Structural Breaks

This paper focuses on the causes of instability of money demand in Tunisia between 1973 and 2013. It has been argued that the main explanatory factors of money demand are national income, monetary market rate and exchange rate. We tested Ambler and McKinnon hypothesis (1985), which assumes that instability is explained by the absence of the nominal exchange rate in the specification of money demand. We found that structural changes are explained by the dependence of the national economy to world shocks, the IMF’s structural adjustment programme at the end of 1986.