Measuring persistence in aggregate output: ARMA models, fractionally integrated ARMA models and nonparametric procedures

Econometric issues in the estimation of persistence in macroeconomic time series are considered. In particular, the relative merits of estimates based on ARMA models, ARFIMA models and nonparametric procedures are investigated. It is shown that ARFIMA models are inappropriate for the purpose of estimating persistence. Furthermore, some of the criticism leveled in the literature against the use of ARMA models for estimating long run properties is put into perspective. Methodological issues arising in the estimation of ARMA models that are relevant to estimation of persistence are discussed. It is shown how overparameterization of an ARMA model may lead to severely downward biased estimates of persistence. The theoretical results are employed to explain some of the findings in Campbell & Mankiw (1987a) and Christiano & Eichenbaum (1990). The methodological aspects of the paper are also relevant for the problem of estimating the value of a spectral density at any given frequency. An empirical study confirms persistence estimates reported in Campbell & Mankiw (1987a), and shows that ARMA models as well as nonparametric procedures give very similar estimates of persistence if properly applied. First version received: May 1996/final version received: March 1998     

Long- versus medium-run identification in fractionally integrated VAR models

We state that long-run restrictions that identify structural shocks in VAR models with unit roots lose their original interpretation if the fractional integration order of the affected variable is below one. For such fractionally integrated models we consider a medium-run approach that employs restrictions on variance contributions over finite horizons. We show for alternative identification schemes that letting the horizon tend to infinity is equivalent to imposing the restriction of Blanchard and Quah (1989) introduced for the unit-root case.     

Forecasting the real output using fractionally integrated techniques

The annual structure of the real GDP in the UK, France, Germany and Italy is examined by means of fractionally integrated techniques. Using a version of a testing procedure due to Robinson (Journal of the American Statistical Association, 84, –37, 1994), it is shown that the series can be specified in terms of I(d?) statistical models with d higher than 1. Thus, the series are nonstationary and non-mean-reverting. The forecasting properties of the selected models for each country are also examined.     

Limiting efficiency of OLS vs. GLS when regressors are fractionally integrated

We show that previous results on the asymptotic efficiency of OLS vs. GLS in the context of trending data carry over to regressors of the fractionally integrated type.     

Testing of unit roots and other fractionally integrated hypotheses in the presence of structural breaks

Tests of unit roots and other nonstationary hypotheses that were proposed by Robinson (1994) are applied in this article to the Nelson and Plosser's (1982) series. The tests can be expressed in a way allowing for structural breaks under both the null and the alternative hypotheses. When applying the tests to the same dataset as in Perron (1989), we observe that our results might be consistent with those in Perron (1989) when testing the nulls of trend-stationarity or a unit-root. However, we also observe that fractionally integrated hypotheses may be plausible alternatives in the context of structural breaks at a known period of time. Final version received: August 2000/Final version accepted: August 2001 RID="*" ID="*"  The author gratefully acknowledges the financial support from the European TMR grant No. ERBFMRX-CT-98-0213. Comments of two anonymous referees are also acknowledged.     

A fractionally integrated exponential STAR model applied to the US real effective exchange rate

The aim of this paper is to study the dynamics of the US real effective exchange rate by capturing non-linearity and long-memory features. In this context, we use the family of fractionally integrated STAR (FISTAR) models proposed by van Dijk et al. (van Dijk, D., Franses, P.H., and Paap, R., 2002. A non-linear longmemory model with an application to US unemployment. Journal of Econometrics 110, 135–165.) in the case when the transition function is an exponential function and we develop an estimation procedure. Indeed, these models can take into account processes characterized by several distinct dynamic regimes and persistence phenomena.     

Optimal steady-state in stationary consumption-loan type models

We consider a stationary overlapping generations economy, and prove that an optimal steady state exists. We show that if a government intervention is needed in order to implement the optimal steady state as a competitive equilibrium, it is necessary only in a finite number of periods. If the interest rate associated with the optimal steady state equals the population rate of growth, some outside money may be required in order to make the competitive equilibrium follow the optimal steady state. We show that our existence result enables us to construct Pareto optimal competitive equilibria in some important cases.     

The persistence of unemployment in the USA and Europe in terms of fractionally ARIMA models

This article examines the persistence of unemployment in the USA and four European countries by means of fractionally integrated ARMA (ARFIMA) models. In doing so, a type of flexibility in modelling low-frequency dynamics not achieved by non-fractionally ARIMA models can be provided. The results indicate that the unemployment series are much more persistent in some countries such as the UK and France, than in others including Germany or the USA.     

The power of tests for equivalent ARMA models: The implications for practitioners

Analysts frequently find it convenient to use the same ARMA model to make forecasts for multiple time series. The trick is to know when it is safe to assume that multiple series are generated by the same underlying process. Although several authors have developed statistical procedures for testing whether two models are equivalent, no one has shown how to determine the power of these tests. This paper shows how to determine the power of the most general test for equivalent ARMA models. It also shows how to quantify the effect of model misspecification errors on the accuracy of the forecast. An illustrative example and flowchart are then used to show how calculating the power of the test can enable the practitioner to safeguard against a serious degradation in the accuracy of the forecast.Jel classification: C12, C22, C53First version received: March 2002/Final version received: December 2002     

A systematic approach for integrated trend analysis—The case of etching

Understanding technology development trends is of critical importance to countries, industries and enterprises to be sustainable in global competition. Attempts have been made to establish trend analysis by bibliometric and patent analyses. Also text-mining uncovers hidden and important information from structured or unstructured documents which serve as knowledge carriers. This study aims to provide a systematic approach for integrated trend analysis that takes into account bibliometric analysis, patent analysis and text-mining analysis. Etching is selected as the case study for integrating trend analysis method proposed in this study. Also, validity and applicability of the integrated analysis are evaluated.     

Calendar effects in structural time series models with trend and season

Calendar effects are analysed in the class of structural time series models one of the two main model based approaches in time series decomposition. While Bell and Hillmer (1983) modeled calendar variation in the ARIMA model based approach, we represent structural models in the generalized regression form which allows to apply classical estimation and test procedures. It turns out that the expected high computaional complexity 0(T ³) in the generalized regression model can be reduced to 0(T). As all parameters are estimated by maximizing the likelihood the Likelihood Ratio statistics can be used to test effects of the calendar composition.     

Existence and efficiency of a stationary subgame-perfect equilibrium in coalitional bargaining models with nonsuperadditive payoffs

We provide the existence theorem of stationary subgame-perfect equilibrium (SSPE) in a noncooperative coalitional bargaining game model with random proposers. Our model contains a bargaining situation where the coalitional game is nonsuperadditive. We also provide a necessary and sufficient condition for the existence of a pure-strategy SSPE satisfying the efficiency property when the discount factor is close to one. Furthermore, we provide examples where the delay in agreement occurs, even in a random-proposers model, when the game is nonsuperadditive. I am grateful to Akira Okada and an anonymous referee for their useful comments and helpful suggestions.     

Improving estimation of the fractionally differencing parameter in the SARFIMA model using tapered periodogram

This paper presents a new method to estimate the fractional differencing parameters in the SARFIMA model. A technique of split cosine bell tapering is suggested to improve the EGPH method. The simulation study shows that the optimal split proportion and bandwidth for the EGPH with split cosine bell tapering method respectively are p = 0.1 and b = 0.9. The new method with the optimal parameters outperforms the EGPH and EGPH with cosine bell tapering. We further applied the EGPH method to estimate intraday volume series and high-frequency absolute return data. The results show that the seasonal fractionally differencing parameters are all estimated to be large, while the nonseasonal fractionally differencing parameters are all very small. This indicates that their long memory property may be mainly caused by the structure of long-range dependence at the seasonal lags instead of dependence at the nonseasonal lags.     

On the Fisher information matrix of a vector ARMA process

We derive a neat and compact representation of the asymptotic Fisher information matrix of a vector ARMA process. Its inverse can be used immediately as the asymptotic covariance matrix of the Gaussian maximum likelihood estimator. We also provide the robust sandwich covariance estimator when the process is non-Gaussian.     

Uniqueness of stationary equilibrium payoffs in coalitional bargaining

We study a model of sequential bargaining in which, in each period before an agreement is reached, the proposer?s identity is randomly determined, the proposer suggests a division of a pie of size one, each other agent either approves or rejects the proposal, and the proposal is implemented if the set of approving agents is a winning coalition for the proposer. The theory of the fixed point index is used to show that stationary equilibrium expected payoffs of this coalitional bargaining game are unique. This generalizes Eraslan [34] insofar as: (a) there are no restrictions on the structure of sets of winning coalitions; (b) different proposers may have different sets of winning coalitions; (c) there may be a positive probability that no proposer is selected.     

Estimating the stationary distribution of a Markov chain

Summary. Let be a Markov chain with a unique stationary distribution . Let h be a bounded measurable function. Write and . This paper explores conditions for the consistency and asymptotic normality of the estimate of of assuming the existence of a solution to the Poisson equation . Our framework covers the case of nonirreducible Markov chains arising in many growth models in economics. Received: October 8, 2001; revised version: April 8, 2002 RID="*" ID="*" Thanks are due to Professors Rabi Bhattacharya, Nicholas Kiefer and Timothy Vogelsang on an earlier draft for helpful conversations, and a referee for insightful comments. Correspondence to: M.Majumdar     

蓄电池的未来发展趋势

分析了储能电池现实需求,铅酸蓄电池和锂电池比较及锂电池储能的特点和应用前景。     

Location models as models of product choice

Markets in which firm choice of product is an economic decision are commonly analyzed using a variant of the location model pioneered by Hotelling (Econ. J.39 (1929), 41–57). This paper develops a framework for formalizing the idea that a set of consumers with preferences defined over an abstract set of commodities can be represented as if they behaved as is typically assumed in the goods-as-locations models. With this framework in place, we are able to derive the preference assumptions underlying the two most common versions of these models, and also to uncover the foundations of the now well-known principle of minimum differentiation.     

A comparison of classical tests of criterion when determining Granger causality with a bivariate ARMA model

The necessary and sufficient conditions for determining Granger causality with a bivariate ARMA model have been presented by Granger (1969), Haugh and Pierce (1977) and Eberts and Steece (1984). However the literature fails to address the question as to which classical test criterion likelihood ratio, Lagrange multiplier, Rao efficient scoring or Wald should be employed. This study addresses this question via a simulation study.The author would like to acknowledge numerous suggestions and insight provided by Bert Steece and Sergio Koreisha, along with two anonymous referees.