A computationally convenient unit root test with covariates, conditional heteroskedasticity and efficient detrending

When testing for a unit root in a time series, in spite of the well-known power problem of univariate tests, it is quite common to use only the information regarding the autoregressive behaviour contained in that series. In a series of influential papers, Elliott et al. (Efficient tests for an autoregressive unit root, Econometrica 64, 813–836, 1996), Hansen (Rethinking the univariate approach to unit root testing: using covariates to increase power, Econometric Theory 11, 1148–1171, 1995a) and Seo (Distribution theory for unit root tests with conditional heteroskedasticity, Journal of Econometrics 91, 113–144, 1999) showed that this practice can be rather costly and that the inclusion of the extraneous information contained in the near-integratedness of many economic variables, their heteroskedasticity and their correlation with other covariates can lead to substantial power gains. In this article, we show how these information sets can be combined into a single unit root test.

Panel versus GARCH information in unit root testing with an application to financial markets

In a search for more powerful unit root tests, some researchers have recently proposed accounting for the information contained in the GARCH of the innovations. However, while promising, tests with GARCH are difficult to implement, which has made them quite uncommon in the empirical literature. A computationally attractive alternative is to account not for GARCH but the information contained in a panel of multiple time series. The purpose of the current note is to compare the relative power achievable from these two information sources. © 2014 Elsevier B.V.

Is there really a unit root in the inflation rate? More evidence from panel data models

Time series unit root evidence suggests that inflation is nonstationary. By contrast, when using more powerful panel unit root tests, Culver and Papell (1997) find that inflation is stationary. In this article, we test the robustness of this result by applying a battery of recent panel unit root tests. The results suggest that the stationarity of inflation holds even after controlling for cross-sectional dependence and structural change.

Testing unit root based on partially adaptive estimation

This paper proposes unit tests based on partially adaptive estimation. The proposed tests provide an intermediate class of inference procedures that are more efficient than the traditional OLS-based methods and simpler than unit root tests based on fully adptive estimation using nonparametric methods. The limiting distribution of the proposed test is a combination of standard normal and the traditional Dickey-Fuller (DF) distribution, including the traditional ADF test as a special case when using Gaussian density. Taking into a account the well documented characteristic of heavy-tail behavior in economic and financial data, we consider unit root tests coupled with a class of partially adaptive M-estimators based on the student-t distributions, wich includes te normal distribution as a limiting case. Monte Carlo Experiments indicate that, in the presence of heavy tail distributions or innovations that are contaminated by outliers, the proposed test is more powerful than the traditional ADF test. We apply the proposed test to several macroeconomic time series that have heavy-tailed distributions. The unit root hypothesis is rejected in U.S. real GNP, supporting the literature of transitory shocks in output. However, evidence against unit roots is not found in real exchange rate and nominal interest rate even haevy-tail is taken into a account.

Essays on mixed-frequency data : forecasting and unit root testing

Doutoramento em Economia

Modified CADF and CIPS panel unit root statistics with standard chi-squared and normal limiting distributions

In an influential paper Pesaran ('A simple panel unit root test in presence of cross-section dependence', Journal of Applied Econometrics, Vol. 22, pp. 265-312, 2007) proposes two unit root tests for panels with a common factor structure. These are the CADF and CIPS test statistics, which are amongst the most popular test statistics in the literature. One feature of these statistics is that their limiting distributions are highly non-standard, making for relatively complicated implementation. In this paper, we take this feature as our starting point to develop modified CADF and CIPS test statistics that support standard chi-squared and normal inference.

Monetary union and productivity differences in mercosur countries

This paper investigates cross-country productivity convergence among Mercosur members plus associates (Chile and Bolivia) and Peru, during the period 1960-1999. The testing strategy is based on the definitions of time-series convergence by Bernard and Durlauf (1995), and applies sequentially the multivariate unit root tests proposed by Sarno and Taylor (1998), Flôres, Preumont and Szafarz (1995) and Breuer, Mc Nown and Wallace (1999). The last two tests allow to identify the countries that converge. Our results show evidence of convergence among the four Mercosur countries, using either Argentina or Brazil as benchmark. Weaker evidence of convergence is also found with Bolivia. The results point out that monetary union among the Southern Cone economies, though a far objective, is not without sense.

Tests of Joint Hypotheses for Time Series Regression with a Unit Root

This Paper Studies Tests of Joint Hypotheses in Time Series Regression with a Unit Root in Which Weakly Dependent and Heterogeneously Distributed Innovations Are Allowed. We Consider Two Types of Regression: One with a Constant and Lagged Dependent Variable, and the Other with a Trend Added. the Statistics Studied Are the Regression \"F-Test\" Originally Analysed by Dickey and Fuller (1981) in a Less General Framework. the Limiting Distributions Are Found Using Functinal Central Limit Theory. New Test Statistics Are Proposed Which Require Only Already Tabulated Critical Values But Which Are Valid in a Quite General Framework (Including Finite Order Arma Models Generated by Gaussian Errors). This Study Extends the Results on Single Coefficients Derived in Phillips (1986A) and Phillips and Perron (1986).

The structure of tourist expenditure in Fiji : evidence from unit root structural break tests

The central aim of this paper is to investigate whether shocks to Fiji's tourism industry have a permanent effect or a transitory effect on tourist expenditure in Fiji. To accomplish this aim the Zivot and Andrews (1992) one break test and the Lumsdaine and Papell (1997) two break tests are used. The one break and two break tests reveal 1987 - the year of the military coups in Fiji - as the year of the break. Moreover, it is possible to reject the unit root null leading to the conclusion that shocks to Fiji's tourism industry have a transitory effect on tourist expenditure in Fiji.

Tests for Cointegration Rank and the Initial Condition

Many economic events involve initial observations that substantially deviate from long-run steady state. Initial conditions of this type have been found to impact diversely on the power of univariate unit root tests, whereas the impact on multivariate tests is largely unknown. This paper investigates the impact of the initial condition on tests for cointegration rank. We compare the local power of the widely used likelihood ratio (LR) test with the local power of a test based on the eigenvalues of the companion matrix. We find that the power of the LR test is increasing in the magnitude of the initial condition, whereas the power of the other test is decreasing. The behaviour of the tests is investigated in an application to price convergence.

PANEL DATA UNIT ROOT TEST WITH FIXED TIME DIMENSION

The consideration of the limit theory in which T is fixed and N is allowed to go to infinity improves the finite-sample properties of the tests and avoids the imposition of the relative rates at which T and N go to infinity.

Testing for a unit root in a process exhibiting a structural break in the presence of GARCH errors

This paper considers the effect of GARCH errors on the tests proposed byPerron (1997) for a unit root in the presence of a structural break. We assessthe impact of degeneracy and integratedness of the conditional varianceindividually and find that, apart from in the limit, the testing procedure isinsensitive to the degree of degeneracy but does exhibit an increasingover-sizing as the process becomes more integrated. When we consider the GARCHspecifications that we are likely to encounter in empirical research, we findthat the Perron tests are reasonably robust to the presence of GARCH and donot suffer from severe over-or under-rejection of a correct null hypothesis.

A nonlinear approach to testing the unit root null hypothesis : an application to international health expenditures

In this article, we examine the unit root null hypothesis for per capita total Health Expenditures (HEs), per capita private HEs and per capita public HEs for 29 Organization for Economic Co-operation and Development (OECD) countries. The novelty of our work is that we use a new nonlinear unit root test that allows for one structural break in the data series. We find that for around 45% of the countries, we are able to reject the unit root hypothesis for each of the three HE series. Moreover, using Monte Carlo simulations, we show that our proposed unit root model has better size and power properties than the widely used Augmented Dickey–Fuller (ADF) and Lagrange Multiplier (LM) type tests.

On the choice of test for a unit root when the errors are conditionally heteroskedastic

It is well known that in the context of the classical regression model with heteroskedastic errors, while ordinary least squares (OLS) is not efficient, the weighted least squares (WLS) and quasi-maximum likelihood (QML) estimators that utilize the information contained in the heteroskedasticity are. In the context of unit root testing with conditional heteroskedasticity, while intuition suggests that a similar result should apply, the relative performance of the tests associated with the OLS, WLS and QML estimators is not well understood. In particular, while QML has been shown to be able to generate more powerful tests than OLS, not much is known regarding the relative performance of the WLS-based test. By providing an in-depth comparison of the tests, the current paper fills this gap in the literature.