nep-ets New Economics Papers
on Econometric Time Series
Issue of 2019‒05‒27
thirteen papers chosen by
Jaqueson K. Galimberti
KOF Swiss Economic Institute

  1. Contagious Switching By Owyang, Michael T.; Piger, Jeremy M.; Soques, Daniel
  2. Cointegration in high frequency data By Simon Clinet; Yoann Potiron
  3. Exogenous uncertainty and the identification of Structural Vector Autoregressions with external instruments By Angelini, Giovanni; Fanelli, Luca
  4. Simultaneous multiple change-point and factor analysis for high-dimensional time series By Barigozzi, Matteo; Cho, Haeran; Fryzlewicz, Piotr
  5. Data-Driven Local Polynomial Trend Estimation for Economic Data - Steady State Adjusting Trends By Marlon Fritz
  6. Data-driven Local Polynomial for the Trend and its Derivatives in Economic Time Series By Yuanhua Feng; Thomas Gries; Marlon Fritz
  7. Are inflation rates in OECD countries actually stationary during 2011-2018? Evidence based on Fourier Nonlinear Unit root tests with Break By Yaya, OlaOluwa S; Ogbonna, Ahamuefula; Atoi, Ngozi V
  8. Hysteresis of Unemployment Rates in Africa: New Findings from Fourier ADF test By Yaya, OlaOluwa S; Ogbonna, Ahamuefula; Mudida, Robert
  9. Modeling the long-run relationship between inflation and economic growth in Zimbabwe: a bi-variate cointegration (Engle-Granger Two-Step) approach By NYONI, THABANI; MUTONGI, CHIPO
  10. Time Series Analysis and Forecasting of the US Housing Starts using Econometric and Machine Learning Model By Sudiksha Joshi
  11. The consumption Euler equation or the Keynesian consumption function? By Anders Rygh Swensen; Pål Boug; Ådne Cappelen; Eilev S. Jansen
  12. On the Use of Spectral Value Decomposition for the Construction of Composite Indices By Luca Farnia
  13. xtserialpm: A portmanteau test for serial correlation in a linear panel model By Jochmans, K.,; Verardi, V.

  1. By: Owyang, Michael T. (Federal Reserve Bank of St. Louis); Piger, Jeremy M. (University of Oregon); Soques, Daniel (University of North Carolina Wilmington)
    Abstract: In this paper, we analyze the propagation of recessions across countries. We construct a model with multiple qualitative state variables that evolve in a VAR setting. The VAR structure allows us to include country-level variables to determine whether policy also propagates across countries. We consider two different versions of the model. One version assumes the discrete state of the economy (expansion or recession) is observed. The other assumes that the state of the economy is unobserved and must be inferred from movements in economic growth. We apply the model to Canada, Mexico, and the U.S. to test if spillover effects were similar before and after NAFTA. We find that trade liberalization has increased the degree of business cycle propagation across the three countries.
    Keywords: time varying transition probabilities; NAFTA; business cycle synchronization
    JEL: C32 E32
    Date: 2019–05–13
  2. By: Simon Clinet; Yoann Potiron
    Abstract: In this paper, we consider a framework adapting the notion of cointegration when two asset prices are generated by a driftless It\^{o}-semimartingale featuring jumps with infinite activity, observed synchronously and regularly at high frequency. We develop a regression based estimation of the cointegrated relations method and show the related consistency and central limit theory when there is cointegration within that framework. We also provide a Dickey-Fuller type residual based test for the null of no cointegration against the alternative of cointegration, along with its limit theory. Under no cointegration, the asymptotic limit is the same as that of the original Dickey-Fuller residual based test, so that critical values can be easily tabulated in the same way. Finite sample indicates adequate size and good power properties in a variety of realistic configurations, outperforming original Dickey-Fuller and Phillips-Perron type residual based tests, whose sizes are distorted by non ergodic time-varying variance and power is altered by price jumps. Two empirical examples consolidate the Monte-Carlo evidence that the adapted tests can be rejected while the original tests are not, and vice versa.
    Date: 2019–05
  3. By: Angelini, Giovanni; Fanelli, Luca
    Abstract: We provide necessary and sufficient conditions for the identification of Structural Vector Autoregressions (SVARs) with external instruments, considering the case in which r instruments are used to identify g structural shocks of interest, r>=g>=1. Novel frequentist estimation methods are discussed by considering both a partial shocks identification strategy, where only g structural shocks are of interest and are instrumented, and in a full shocks identification strategy, where despite g structural shocks are instrumented, all n structural shocks of the system can be identified under certain conditions. The suggested approach is applied to empirically investigate whether financial and macroeconomic uncertainty can be approximated as exogenous drivers of U.S. real economic activity, or rather as endogenous responses to first moment shocks, or both. We analyze whether the dynamic causal effects of non-uncertainty shocks on macroeconomic and financial uncertainty are signicant in the period after the Global Financial Crisis.
    Keywords: Exogenous Uncertainty, External Instruments, Identification, proxy-SVAR, SVAR.
    JEL: C32 C51 E44 G10
    Date: 2018–05
  4. By: Barigozzi, Matteo; Cho, Haeran; Fryzlewicz, Piotr
    Abstract: We propose the first comprehensive treatment of high-dimensional time series factor models with multiple change-points in their second-order structure. We operate under the most flexible definition of piecewise stationarity, and estimate the number and locations of change-points consistently as well as identifying whether they originate in the common or idiosyncratic components. Through the use of wavelets, we transform the problem of change-point detection in the second-order structure of a high-dimensional time series, into the (relatively easier) problem of change-point detection in the means of high-dimensional panel data. Also, our methodology circumvents the difficult issue of the accurate estimation of the true number of factors in the presence of multiple change-points by adopting a screening procedure. We further show that consistent factor analysis is achieved over each segment defined by the change-points estimated by the proposed methodology. In extensive simulation studies, we observe that factor analysis prior to change-point detection improves the detectability of change-points, and identify and describe an interesting ‘spillover’ effect in which substantial breaks in the idiosyncratic components get, naturally enough, identified as change-points in the common components, which prompts us to regard the corresponding change-points as also acting as a form of ‘factors’. Our methodology is implemented in the R package factorcpt, available from CRAN.
    Keywords: piecewise stationary factor model; change-point detection; principal component analysis; wavelet transformation; Double CUSUM Binary Segmentation
    JEL: C1
    Date: 2018–09
  5. By: Marlon Fritz (University of Paderborn)
    Abstract: Economic variables usually follow a dynamic trend pattern. However, it is difficult to estimate this trend precisely as numerous economically- and statistically-based estimation methods exist. This contribution proposes a data-driven nonparametric trend estimator that is local polynomial, to improve arbitrary trend estimations of commonly used methods with respect to the selection of the smoothing parameter and the dependence structure. An iterative plug-in (IPI) algorithm determines the bandwidth endogenously and allows a theory-based interpretation of the length of growth processes. To demonstrate the power of this local polynomial trend estimation approach, an extensive simulation study is performed. Furthermore, an example using UK GDP data along with a detailed manual for empirical application is provided. Smaller error criterion values, adequate detection of the true data generating process (DGP), simplicity and availability favor this purely data-driven local polynomial trend estimation method.
    Keywords: Nonparametric Model, Nonstationary Process, Time Series Models, Empirical Growth Trends
    JEL: C14 C22 O47
    Date: 2019–02
  6. By: Yuanhua Feng (University of Paderborn); Thomas Gries (University of Paderborn); Marlon Fritz (University of Paderborn)
    Abstract: The main purpose of this paper is the development of iterative plug-in algorithms for local polynomial estimation of the trend and its derivatives under dependent errors. In particular, a data-driven lag-window estimator for the variance factor is proposed so that the nonparametric stage is carried out without any parametric assumption on the stationary errors. Moreover, confidence bounds for the trend and its derivatives are conducted using some asymptotically unbiased estimates. Analysis of the residuals using an ARMA model is further discussed in detail. Practical performance of the proposals is confirmed by a simulation study and illustrated by quarterly US and UK GDP data. An R package called “smoots” (smoothing time series) for smoothing the trend and its derivatives in short memory time series is developed based on the proposals of this paper.
    Keywords: Bandwidth selection, dependent errors, derivative estimation, IPI for spectral density, semiparametric modelling, implementation in R
    JEL: C14 C22 O40
    Date: 2019–04
  7. By: Yaya, OlaOluwa S; Ogbonna, Ahamuefula; Atoi, Ngozi V
    Abstract: We re-investigate the hypothesis of inflation stationarity in 33 Organization of Economic Cooperation and Development (OECD) member countries from 2011 to 2018. We compare two linear fractional-based, two nonlinear Fourier-based and two nonlinear Fourier-Fractional-based unit root tests with five classical unit root tests. Classical unit root tests are biased to the hypothesis of unit root since they do not account for structural breaks and nonlinearities. Incorporating just the Fourier framework into the ADF test does not significantly improve the conventional ADF unit root test. More importantly, we find that accounting for the observed limitations of the classical unit root tests improves the power of test. The rejection ability of the examined unit root tests are greatly enhanced whenever inherent salient features (nonlinearity and fractional integration) are combined with structural breaks. The battery of enhanced unit root tests confirmed the Norwegian inflation rate as the only nonstationary series among the thirty three considered. More than half of the OECD member countries have inflation rates that are somewhat stationary within the investigated period. Robustness check indicated the superiority of test regression with Fourier nonlinearity and break over the classical ADF regression.
    Keywords: Fourier function; Inflation rates; Nonlinearity; OECD countries; Unit root test
    JEL: C2 C22
    Date: 2019–02
  8. By: Yaya, OlaOluwa S; Ogbonna, Ahamuefula; Mudida, Robert
    Abstract: We investigate unit root in the unemployment rates of 42 African countries. The essence is to clarify if the hypothesis of hysteresis holds or unemployment rate is dubbed as having natural rate, that is, stationarity. Having considered a novel approach that considers the nonlinear Fourier and a structural break in the unit root testing framework, we find the classical unit root test wrongly accepting the hysteresis hypothesis of unemployment rate in selected African countries more than 60% of the cases. Meanwhile, our approach finds fewer cases of hysteresis in the unemployment rate than initially detected by the conventional classical test: the hysteresis hypothesis is found to hold in only 7 countries (Algeria, Botswana, Cabo Verde, Congo DR, Guinea-Bissau, Liberia and Tanzania) out of the 42 African countries. This implies that with the exception of the seven countries mentioned, shocks to unemployment will be transitory and strong policy action will not be required to address unemployment challenges. This suggests that hysteresis effects will be offset in overall since these are concentrated in smaller African economies and portends for a faster recovery to shocks in the broader African context. Robustness check proves the superiority of the Fourier unit root tests with structural break over other lower alternatives.
    Keywords: Africa; Fourier function; Hysteresis hypothesis; Structural breaks; Natural rate of unemployment; Unemployment rate; Unit root test
    JEL: C22 E2 E24 J4 J6 J64
    Date: 2019–02
    Abstract: The debate on the nexus between economic growth and inflation is generally inconclusive and yet inevitably interesting. This study makes a contribution to the existing debate by empirically investigating the relationship between inflation and economic growth in the context of Zimbabwe. Using time series data spanning from 1960 up to 2017, the study employs the Engle – Granger Two Step modeling technique in order to analyze the relationship between inflation and economic growth in Zimbabwe. Our findings indicate that there is a negative and statistically significant relationship between inflation and economic growth both in the short – run and long – run. The speed of adjustment to equilibrium is approximately 62% annually when the variables wander away from their equilibrium values. Amongst other policy prescriptions, the study recommends inflation targeting policy in order to stimulate growth while maintaining price stability in Zimbabwe.
    Keywords: Cointegration; economic growth; Error Correction Mechanism (ECM); inflation; Zimbabwe
    JEL: E31 E37
    Date: 2019–05–08
  10. By: Sudiksha Joshi
    Abstract: In this research paper, I have performed time series analysis and forecasted the monthly value of housing starts for the year 2019 using several econometric methods - ARIMA(X), VARX, (G)ARCH and machine learning algorithms - artificial neural networks, ridge regression, K-Nearest Neighbors, and support vector regression, and created an ensemble model. The ensemble model stacks the predictions from various individual models, and gives a weighted average of all predictions. The analyses suggest that the ensemble model has performed the best among all the models as the prediction errors are the lowest, while the econometric models have higher error rates.
    Date: 2019–05
  11. By: Anders Rygh Swensen; Pål Boug; Ådne Cappelen; Eilev S. Jansen (Statistics Norway)
    Abstract: We formulate a general cointegrated vector autoregressive (CVAR) model that nests both a class of consumption Euler equations and various Keynesian type consumption functions. Using likelihoodbased methods and Norwegian data, we find support for cointegration between consumption, income and wealth once a structural break around the financial crisis is allowed for. That consumption cointegrates with both income and wealth and not only with income points to the empirical irrelevance of an Euler equation. Moreover, we find that consumption equilibrium corrects to changes in income and wealth and not that income equilibrium corrects to changes in consumption, which would be the case if an Euler equation is true. We also find that most of the parameters stemming from the class of Euler equations are not corroborated by the data when considering conditional expectations of future consumption and income in CVAR models. Only habit formation seems important in explaining the Norwegian consumer behaviour. Our preferred model is a dynamic Keynesian type consumption function with a first year marginal propensity to consume out of income close to 25 per cent.
    Keywords: Consumption Euler equation; Keynesian consumption function; financial crisis; structural break; conditional expectations
    JEL: C51 C52 E21
    Date: 2019–04
  12. By: Luca Farnia (Fondazione Eni Enrico Mattei)
    Abstract: High dimensional composite index makes experts’ preferences in set-ting weights a hard task. In the literature, one of the approaches to derive weights from a data set is Principal Component or Factor Analysis that, although conceptually different, they are similar in results when FA is based on Spectral Value Decomposition and rotation is not performed. This works motivates theoretical reasons to derive the weights of the elementary indicators in a composite index when multiple components are retained in the analysis. By Monte Carlo simulation it offers, moreover, the best strategy to identify the number of components to retain.
    Keywords: Composite Index, Weighting, Correlation Matrix, Principal Com-ponent, Factor Analysis
    JEL: C38 C43 C15
    Date: 2019–05
  13. By: Jochmans, K.,; Verardi, V.
    Abstract: We introduce the command xtserialpm to perform the portmanteau test developed in Jochmans (2019). The procedure tests for serial correlation in the errors of a linear panel model after estimation of the regression coefficients by the within-group estimator. The test is different from the test of Inoue and Solon (2006) that is performed by xtistest (Wursten 2018) in that it allows for heteroskedasticity. In simulations documented below, xtserialpm is found to provide a much more powerful test than xtistest. xtserialpm can deal with unbalanced panel data.
    Keywords: xtserialpm, heteroskedasticity, fixed-effect model, portmanteau test, serial correlation, short panel data, unbalanced panelexponential regression, gravity model, panel data, two-way fixed effects
    JEL: C33 C87
    Date: 2019–04–26

This nep-ets issue is ©2019 by Jaqueson K. Galimberti. 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.