nep-ets New Economics Papers
on Econometric Time Series
Issue of 2006‒08‒26
twenty-one papers chosen by
Yong Yin
SUNY at Buffalo

  1. A Panel Unit Root and Panel Cointegration Test of the Complementarity Hypothesis in the Mexican Case, 1960-2001 By Miguel D. Ramirez
  2. Iterative plug-in algorithms for SEMIFAR models - definition, convergence and asymptotic properties By Jan Beran; Yuanhua.Feng
  3. Optimal Convergence Rates in Nonparametric Regression with Fractional Time Series Errors By Yuanhua Feng
  4. Kernel smoothed prediction intervals for ARMA models By Klaus Abberger
  5. An Iterative Plug-In Algorithm for Nonparametric Modelling of Seasonal Time Series By Yuanhua Feng
  6. Smoothing ordered sparse contingency tables and the Chi-Squared test By Klaus Abberger
  7. Prediction of 0-1-events for short- and long-memory time series By Jan Beran
  8. Simultaneously Modelling Conditional Heteroskedasticity and Scale Change By Yuanhua Feng
  9. Recent Developments in Non- and Semiparametric Regression with Fractional Time Series Errors By Jan Beran; Yuanhua.Feng
  10. Modelling Different Volatility Components in High-Frequency Financial Returns By Yuanhua Feng
  11. Conditionally parametric fits for CAPM betas By Klaus Abberger
  12. Why Do Asset Prices Not Follow Random Walks? By Günter Franke; Erik Lüders
  13. A Sequential Quadratic Programming Method for Volatility Estimation in Option Pricing By Bertram Düring; Ansgar Jüngel; S. Volkwein
  14. Beveridge-Nelson Decomposition with Markov Switching By Chin Nam Low; Heather Anderson; Ralph D. Snyder
  15. Approximately Normal Tests for Equal Predictive Accuracy in Nested Models By Kenneth D. West; Todd Clark
  16. Intra-Day Seasonality in Activities of the Foreign Exchange Markets: Evidence From the Electronic Broking System By Takatoshi Ito; Yuko Hashimoto
  17. A Random Coefficients Autoregressive Model with Exogenously-Driven Stochastic Unit Roots By J. Isaac Miller
  18. Structural Breaks in Trade and Income Per Capita in ASEAN-5 Countries: An Application of Innovational Outlier Models By Jayanthakumaran, Kankesu; Pahlavani, Mosayeb
  19. The Interplay Between the Thai and Several Other International Stock Markets By Valadkhani, Abbas; Chancharat, Surachai; Harvie, Charles
  20. Spurious Regressions With Time-Series data: Further Asymptotic Results By David E. A. Giles
  21. Excess Volatility in European Equity Style Indices - New Evidence By Marian Berneburg

  1. By: Miguel D. Ramirez (Department of Economics, Trinity College)
    Abstract: Using panel data, this paper tests whether public and private capital have a positive and significant effect on aggregate output and labor productivity for Mexico during the 1960-2001 period. The richer information set made possible by the sectorial data enables this study to utilize the methodologically sound “group-mean” Fully Modified Ordinary Least Squares (FMOLS) procedure developed by Pedroni to generate consistent estimates of the relevant panel variables in the cointegrated production (labor productivity) function. The results suggest that, in the long run, changes in the stocks of public and private capital and the economically active population (EAP) have a positive and economically significant effect on output ( and labor productivity). The period is also broken down into two sub-periods: 1960-81 (state-led industrialization) and 1982-2001 (neoliberal model). The estimate for the public capital variables clearly shows that it had a relatively more important economic effect during the earlier state-led period.
    Keywords: Fully Modified Ordinary Least Squares (FMOLS), Panel Unit Roots, Panel Cointegration Test, Complementarity Hypothesis, Mexican Labor Productivity
    JEL: O10 O50 O40
    Date: 2006–08
  2. By: Jan Beran (Department of Mathematics and Statistics, University of Konstanz); Yuanhua.Feng (Department of Mathematics and Statistics, University of Konstanz)
    Abstract: In this paper data-driven algorithms for fitting SEMIFAR models (Beran, 1999) are proposed. The algorithms combine the data-driven estimation of the nonparamet- ric trend and maximum likelihood estimation of the parameters. Convergence and asymptotic properties of the proposed algorithms are investigated. A large simulation study illustrates the practical performance of the methods.
    Keywords: semiparametric models, long-range dependence, fractional ARIMA, antipersistence, nonparametric regression, bandwidth selection
  3. By: Yuanhua Feng (Department of Mathematics and Statistics, University of Konstanz)
    Keywords: Nonparametric regression, optimal convergence rate, long memory, antipersistence, inverse process.
  4. By: Klaus Abberger (IFO Munich)
    Abstract: The procedures of estimating prediction intervals for ARMA processes can be divided into model based methods and empirical methods. Model based methods require knowledge of the model and the underlying innovation distribution. Empirical methods are based on the sample forecast errors. In this paper we apply nonparametric quantile regression to the empirical forecast errors using lead time as regressor. With this method there is no need for a distribution assumption. But for the data pattern in this case a double kernel method which allows smoothing in two directions is required. An estimation algorithm is presented and applied to some simulation examples.
    Keywords: Forecasting, Prediction intervals, Non normal distributions, Nonparametric estimation, Quantile regression
  5. By: Yuanhua Feng (Department of Mathematics and Statistics, University of Konstanz)
    Abstract: This paper focuses on developing a new data-driven procedure for decomposing seasonal time series based on local regression. Formula of the asymptotic optimal bandwidth hA in the current context is given. Methods for estimating the unknowns in hA are investigated. A data-driven algorithm for decomposing seasonal time series is proposed based on the iterative plug-in idea introduced by Gasser et al. (1991). Asymptotic behaviour of this algorithm is investigated. Some computational aspects are discussed in detail. Practical performance of the proposed algorithm is illustrated by simulated and data examples. The results here also provide some insights into the iterative plug-in idea.
    Keywords: Time series decomposition, Local regression, Iterative plug-in, Bandwidth selection
  6. By: Klaus Abberger (IFO Munich)
    Abstract: To estimate cell probabilities for ordered sparse contingency tables several smooth- ing techniques have been investigated. It has been recognized that nonparametric smoothing methods provide estimators of cell probabilities that have better performance than the pure frequency estimators. With the help of simulation examples it is shown in this paper that these smoothing techniques may help to get test which are more powerful than Chi-Squared test with raw data. But the distribution of the Chi-Squared statistics after smoothing is unknown. This distribution can also be estimated by simulation methods.
    Keywords: nonparametric estimation, local polynomial smoothers, local likelihood, sparse contingency tables, Chi-Squared test, independence test
  7. By: Jan Beran (Department of Mathematics and Statistics, University of Konstanz)
    Abstract: The problem of predicting 0-1-events is considered under general conditions, including stationary processes with short and long memory as well as processes with changing distribution patterns. Nonparametric estimates of the probability function and prediction intervals are obtained.
    Keywords: 0-1-events, long-range dependence, short-range dependence, antipersistence, kernel smoothing, bandwidth, prediction
  8. By: Yuanhua Feng (Department of Mathematics and Statistics, University of Konstanz)
    Abstract: This paper proposes a semiparametric approach by introducing a smooth scale function into the standard GARCH model so that conditional heteroskedasticity and scale change in a financial time series can be modelled simultaneously. An estimation procedure combining kernel estimation of the scale function and maximum likelihood estimation of the GARCH parameters is proposed. Asymptotic proper- ties of the kernel estimator are investigated in detail. An iterative plug-in algorithm is developed for selecting the bandwidth. Practical performance of the proposal is illustrated by simulation. The proposal is applied to the daily S&P 500 and DAX 100 returns. It is shown that there are simultaneously significant conditional heteroskedasticity and scale change in these series.
    Keywords: Semiparametric GARCH, conditional heteroskedasticity, scale change, nonparametric regression with dependence, bandwidth selection
    JEL: C22 C14
  9. By: Jan Beran (Department of Mathematics and Statistics, University of Konstanz); Yuanhua.Feng (Department of Mathematics and Statistics, University of Konstanz)
    Abstract: This paper summarizes recent developments in non- and semiparametric regres- sion with stationary fractional time series errors, where the error process may be short-range, long-range dependent or antipersistent. The trend function in this model is estimated nonparametrically, while the dependence structure of the error process is estimated by approximate maximum likelihood. Asymptotic properties of these estimators are described briefly. The focus is on describing the developments of bandwidth selection in this context based on the iterative plug-in idea (Gasser et al., 1991) and some detailed computational aspects. Applications in the framework of the SEMIFAR (semiparametric fractional autoregressive) model (Beran, 1999) illustrate the practical usefulness of the methods described here.
    Keywords: Nonparametric regression, FARIMA error processes, bandwidth selection, iterative plug-in, SEMIFAR model
  10. By: Yuanhua Feng (Department of Mathematics and Statistics, University of Konstanz)
    Abstract: This paper considers simultaneous modelling of seasonality, slowly changing un- conditional variance and conditional heteroskedasticity in high-frequency financial returns. A new approach, called a seasonal SEMIGARCH model, is proposed to perform this by introducing multiplicative seasonal and trend components into the GARCH model. A data-driven semiparametric algorithm is developed for estimating the model. Asymptotic properties of the proposed estimators are investigated brie y. An approximate significance test of seasonality and the use of Monte Carlo confidence bounds for the trend are proposed. Practical performance of the proposal is investigated in detail using some German stock price returns. The approach proposed here provides a useful semiparametric extension of the GARCH model.
    Keywords: High-frequency financial data, nonparametric regression, seasonality in volatility, semiparametric GARCH model, trend in volatility
  11. By: Klaus Abberger (IFO Munich)
    Abstract: The CAPM model assumes stock returns to be a linear function of the market return. However, there is considerable evidence that the beta stability assumption commonly used when estimating the model is invalid. Nonparametric regression methods are used to examine the stability of beta coefcients in German stock returns. Since local polynomial regression is used for estimation, known methods for testing the stability and for bandwidth choice can be used. For some returns the test indicates time-varying betas. For these returns conditionally parametric fits are calculated.
    Keywords: CAPM, time-varying betas, conditionally parametric fits, nonparametric regression
  12. By: Günter Franke (Department of Economics, University of Konstanz); Erik Lüders (Pinehill Capital and Laval University)
    Abstract: This paper analyzes the e¤ect of non-constant elasticity of the pricing kernel on asset return characteristics in a rational expectations model. It is shown that declining elasticity of the pricing kernel can lead to predictability of asset returns and high and persistent volatility. Also, declining elasticity helps to motivate technical analysis and to explain stock market crashes. Moreover, based on a general characterization of the pricing kernel, we propose analytical asset price processes which can be tested empirically. The numerical analysis reveals strong deviations from the geometric Brownian motion which are caused by declining elasticity of the pricing kernel.
    Keywords: Pricing Kernel, Viable asset price processes, Serial correlation, Heteroskedasticity, Stock market crashes
    JEL: G12
    Date: 2005–08–18
  13. By: Bertram Düring (University of Mainz); Ansgar Jüngel (University of Mainz); S. Volkwein
    Abstract: Our goal is to identify the volatility function in Dupire's equation from given option prices. Following an optimal control approach in a Lagrangian framework, we propose a globalized sequential quadratic programming (SQP) algorithm with a modied Hessian { to ensure that every SQP step is a descent direction { and implement a line search strategy. In each level of the SQP method a linear{quadratic optimal control problem with box constraints is solved by a primal{dual active set strategy. This guarantees L1 constraints for the volatility, in particular assuring its positivity. The proposed algorithm is founded on a thorough rst{ and second{order optimality analysis. We prove the existence of local optimal solutions and of a Lagrange multiplier associated with the inequality constraints. Furthermore, we prove a sucient second-order optimality condition and present some numerical results underlining the good properties of the numerical scheme.
    Keywords: Dupire equation, parameter identication, optimal control, optimality conditions, SQP method, primal-dual active set strategy
    Date: 2006–03–29
  14. By: Chin Nam Low; Heather Anderson; Ralph D. Snyder
    Abstract: This paper considers Beveridge-Nelson decomposition in a context where the permanent and transitory components both follow a Markov switching process. Our approach incorporates Markov switching into a single source of error state-space framework, allowing business cycle asymmetries and regime switches in the long run multiplier.
    Keywords: Beveridge-Nelson decomposition, Markov switching, Single source of error state space models
    JEL: C22 C51 E32
    Date: 2006–08
  15. By: Kenneth D. West; Todd Clark
    Abstract: Forecast evaluation often compares a parsimonious null model to a larger model that nests the null model. Under the null that the parsimonious model generates the data, the larger model introduces noise into its forecasts by estimating parameters whose population values are zero. We observe that the mean squared prediction error (MSPE) from the parsimonious model is therefore expected to be smaller than that of the larger model. We describe how to adjust MSPEs to account for this noise. We propose applying standard methods (West (1996)) to test whether the adjusted mean squared error difference is zero. We refer to nonstandard limiting distributions derived in Clark and McCracken (2001, 2005a) to argue that use of standard normal critical values will yield actual sizes close to, but a little less than, nominal size. Simulation evidence supports our recommended procedure.
    JEL: C22 C53 E17 F37
    Date: 2006–08
  16. By: Takatoshi Ito; Yuko Hashimoto
    Abstract: This paper examines intra-day patterns of the exchange rate behavior, using the “firm” bid-ask quotes and transactions of USD-JPY and Euro-USD recorded in the electronic broking system of the spot foreign exchange markets. The U-shape of intra-day activities (deals and price changes) and return volatility is confirmed for Tokyo and London participants, but not for New York participants. Activities and volatility do not increase toward the end of business hours in the New York market, even on Fridays (ahead of weekend hours of non-trading). It is found that there exists a high positive correlation between volatility and activities and a negative correlation between volatility and the bid-ask spread. A negative correlation is observed between the number of deals and the width of bid-ask spread during business hours.
    JEL: F31 F33 G15
    Date: 2006–08
  17. By: J. Isaac Miller (Department of Economics, University of Missouri-Columbia)
    Abstract: We develop a random coefficients autoregressive (RCA) model with time-varying coefficients generated by a bounded nonlinear function of an exogenous time series that may be a mixingale or integrated. Moreover, we allow for exogenously-driven heteroskedasticity in the error term. By restricting the range of the function essentially to the unit interval, we show that the two series of autoregressive coefficients and variances of such a model are covariance stationary, even though these series may be nonergodic. Time series driven by such a data generating process are stationary, but may have (stochastic) unit or near-unit roots over periods of time. Under appropriate assumptions, we show that maximum likelihood estimation yields asymptotically normal or mixed normal parameter estimates. A data generating process of this form may engender commonly observed time series characteristics that defy the simple I(0)-I(1) dichotomy, but is more structural in nature than statistical I(d) models. Moreover, this approach provides a nonspurious way to model relationships between a nonstationary and a stationary time series. The utility of the proposed econometric model is demonstrated with an empirical application, in which inflation drives the autoregressive coefficient of interest rate volatility.
    Keywords: random coefficients autoregressive models, stochastic unit roots, nonlinear transformations, mixingales, near-epoch dependent processes, integrated processes, interest rate volatility
    JEL: C13 C22 C32
    Date: 2006–01–15
  18. By: Jayanthakumaran, Kankesu (University of Wollongong); Pahlavani, Mosayeb (University of Wollongong)
    Abstract: The founder members of the Association of Southeast Asian Nations (ASEAN-5) – Malaysia, Indonesia, Thailand, the Philippines and Singapore – increasingly adopted outward-oriented policies in trade and investment by enforcing reforms in the mid-1980s. This paper investigates the existence of endogenously determined structural breaks of the trade and income per capita by using historical time series data during the period from 1970 to 2003 for the ASEAN-5 by applying an Innovational Outliner (IO) model in the presence of a potential structural break. We find that significant structural breaks occurred for trade per capita in the mid-1980s, which coincides with the recession in the region. We also find that significant structural breaks occurred for Gross National Income (GNI) per capita in 1997, which coincides with the Asian crisis. The Philippines experienced structural breaks in 1985, which coincides with a recession.
    Keywords: Trade and GDP per capita, IO model, structural break
    JEL: C32 F15 O40
    Date: 2006
  19. By: Valadkhani, Abbas (University of Wollongong); Chancharat, Surachai (University of Wollongong); Harvie, Charles (University of Wollongong)
    Abstract: The paper analyses the effect of various international stock market price indices and some relevant macroeconomic variables on the Thai stock market price index, using a GARCH-M model and monthly data from January 1988 to December 2004. It is found, inter alia, that (a) changes in stock market returns in Singapore, Malaysia and Indonesia in the pre-1997 Asian crisis, and changes in Singapore, the Philippines and Korea in the post-1997 era instantaneously influenced returns in the Thai stock market; (b) changes in the price of crude oil negatively impacted on the Thai stock market only in the pre-Asian crisis period; (c) volatility clustering (i.e. ARCH and GARCH effects) as well as a GARCH-M model were statistically significant only in the pre-1997 era; and (d) stock markets outside the region had no significant immediate impact on monthly aggregate returns in the Thai stock market.
    Keywords: Stock market; conditional volatility; macroeconomic variables; GARCH; Thailand
    JEL: E44 G14 G15
    Date: 2006
  20. By: David E. A. Giles (Department of Economics, University of Victoria)
    Abstract: A “spurious regression” is one in which the time-series variables are non-stationary and independent. It is well-known that in this context the OLS parameter estimates and the R2 converge to functionals of Brownian motions; the “t-ratios” diverge in distribution; and the Durbin-Watson statistic converges in probability to zero. We derive corresponding results for some common tests for the Normality and homoskedasticity of the errors in a spurious regression.
    Keywords: Spurious regression, normality, homoskedasticity, asymptotic theory, unit roots
    JEL: C12 C22 C52
    Date: 2006–08–17
  21. By: Marian Berneburg
    Abstract: Are financial markets efficient? One proposition that seems to contradict this is Shiller’s finding of excess volatility in asset prices and its resulting rejection of the discounted cash flow model. This paper replicates Shiller’s approach for a different data set and extends his analysis by testing for a long-run relationship by means of a cointegration analysis. Contrary to previous studies, monthly data for an integrated European stock market is being used, with special attention to equity style investment strategies. On the basis of this analysis’ results, Shiller’s findings seem questionable. While a long-run relationship between prices and dividends can be observed for all equity styles, a certain degree, but to a much smaller extent than in Shiller’s approach, of excess volatility cannot be rejected. But it seems that a further relaxation of Shiller’s assumptions would completely eliminate the finding of an overly strong reaction of prices to changes in dividends. Two interesting side results are, that all three investment styles seem to have equal performance when adjusting for risk, which by itself is an indication for efficiency and that market participants seem to use current dividend payments from one company as an indication for future dividend payments by other firms. Overall the results of this paper lead to the conclusion that efficiency cannot be rejected for an integrated European equity market.
    Date: 2006–08

This nep-ets issue is ©2006 by Yong Yin. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.