A Stationarity Test in the Presence of an Unknown Number of Smooth Breaks

Abstract. Macroeconomic variables have been shown to display a wide variety of structural breaks of unknown number, duration and form. This poses a challenge since improperly modelled breaks can result in a seriously misspecified model. In this paper, we develop a new test for stationarity that approximates the unknown form of structural breaks using a selected frequency component from a Fourier approximation. Our proposed test performs quite well when breaks are gradual, and shows reasonable power. The appropriate use of the test is illustrated by examining real exchange rates in the post‐Bretton Woods period.     

Testing for a unit root under errors with just barely infinite variance

Abstract. This article investigates the problem of testing for a unit root in the case that the error, {u_t}, of the model is a strictly stationary, mixing process with just barely infinite variance. Such errors have the property that for every δ such that 0 ≤ δ < 2, the moments E|u_t|^δ are finite. Under some additional restrictions on the rate of decay of the mixing rates, these errors belong to the domain of the non‐normal attraction of the normal law and obey the invariance principle. This in turn implies that there might be conditions under which the usual Phillips‐type test statistics for unit roots may still converge to the corresponding Dickey–Fuller distributions. In such a case, the unit‐root hypothesis can be tested within an infinite‐variance framework without any modifications to either the tests themselves or the critical values employed. This article derives a necessary and sufficient condition for convergence of the standard test statistics to the Dickey–Fuller distributions. By means of Monte Carlo simulations, the article also shows that this condition is likely to hold in the case that {u_t} is a serially correlated, integrated generalized autoregressive conditionally heteroskedastic (IGARCH) process and the standard unit‐root tests work well.     

Combining non‐cointegration tests

The local power of many popular non‐cointegration tests has recently been shown to depend on a certain nuisance parameter. Depending on the value of that parameter, different tests perform best. This paper suggests combination procedures with the aim of providing meta tests that maintain high power across the range of the nuisance parameter. 1 We demonstrate the local power of the new meta tests to be in general almost as high as that of the most powerful of the underlying tests. When the underlying tests have similar power, the meta tests even appear more powerful than the best underlying test. At the same time, our new meta tests avoid the arbitrary decision which test to use if individual test results conflict. Moreover it avoids the size distortion inherent in separately applying multiple tests for cointegration to the same dataset. We use the new tests to investigate 286 datasets from published cointegration studies. There, in one‐third of all cases individual tests give conflicting results whereas our meta tests provide an unambiguous test decision.     

Seasonal Unit Root Tests Under Structural Breaks*

Abstract. In this paper, several seasonal unit root tests are analysed in the context of structural breaks at known time and a new break corrected test is suggested. We show that the widely used HEGY test, as well as an LM variant thereof, are asymptotically robust to seasonal mean shifts of finite magnitude. In finite samples, however, experiments reveal that such tests suffer from severe size distortions and power reductions when breaks are present. Hence, a new break corrected LM test is proposed to overcome this problem. Importantly, the correction for seasonal mean shifts bears no consequence on the limiting distributions, thereby maintaining the legitimacy of canonical critical values. Moreover, although this test assumes a breakpoint a priori, it is robust in terms of misspecification of the time of the break. This asymptotic property is well reproduced in finite samples. Based on a Monte‐Carlo study, our new test is compared with other procedures suggested in the literature and shown to hold superior finite sample properties.     

Testing the Null of Co‐integration in the Presence of Variance Breaks

Abstract. We show that changes in the innovation covariance matrix of a vector of series can generate spurious rejections of the null hypothesis of co‐integration when applying standard residual‐based co‐integration tests. A bootstrap solution to the inference problem is suggested which is shown to perform well in practice, redressing the size problems associated with the standard test but not losing power relative to the standard test under the alternative.     

Bootstrap Unit‐Root Tests: Comparison and Extensions

Abstract. In this article, we study and compare the properties of several bootstrap unit‐root tests recently proposed in the literature. The tests are Dickey–Fuller (DF) or Augmented DF, based either on residuals from an autoregression and the use of the block bootstrap or on first‐differenced data and the use of the stationary bootstrap or sieve bootstrap. We extend the analysis by interchanging the data transformations (differences vs. residuals), the types of bootstrap and the presence or absence of a correction for autocorrelation in the tests. We show that two sieve bootstrap tests based on residuals remain asymptotically valid. In contrast to the literature which focuses on a comparison of the bootstrap tests with an asymptotic test, we compare the bootstrap tests among themselves using response surfaces for their size and power in a simulation study. This study leads to the following conclusions: (i) augmented DF tests are always preferred to standard DF tests; (ii) the sieve bootstrap performs better than the block bootstrap; (iii) difference‐based tests appear to have slightly better size properties, but residual‐based tests appear more powerful.     

Inference in Autoregression under Heteroskedasticity

Abstract. A scalar pth‐order autoregression (AR(p)) is considered with heteroskedasticity of the unknown form delivered by a transition function of time. A limit theory is developed and three heteroskedasticity‐robust test statistics are proposed for inference, one of which is based on the nonparametric estimation of the variance function. The performance of the resulting testing procedures in finite samples is compared in simulations and some suggestions for practical application are given.     

Evaluating Specification Tests for Markov‐Switching Time‐Series Models

Abstract. We evaluate the performance of several specification tests for Markov regime‐switching time‐series models. We consider the Lagrange multiplier (LM) and dynamic specification tests of Hamilton (1996) and Ljung–Box tests based on both the generalized residual and a standard‐normal residual constructed using the Rosenblatt transformation. The size and power of the tests are studied using Monte Carlo experiments. We find that the LM tests have the best size and power properties. The Ljung–Box tests exhibit slight size distortions, though tests based on the Rosenblatt transformation perform better than the generalized residual‐based tests. The tests exhibit impressive power to detect both autocorrelation and autoregressive conditional heteroscedasticity (ARCH). The tests are illustrated with a Markov‐switching generalized ARCH (GARCH) model fitted to the US dollar–British pound exchange rate, with the finding that both autocorrelation and GARCH effects are needed to adequately fit the data.     

TESTING FOR THE RANDOMNESS OF AUTOREGRESSIVE COEFFICIENTS

Abstract. Two tests are proposed for the hypothesis that data come from an autoregression against the hypothesis that they come from a random coefficient autoregression. The tests are derived from a consideration of the C(α ) tests of Neyman, the analysis of tests based on the likelihood ratio being complicated by the fact that the vector of system parameters specified under the null hypothesis lies on the boundary of the parameter space. The asymptotic distributional properties are derived and the powers of the tests compared.     

Robust Hypothesis Testing and Robust Time Series Interpolation And Regression

Abstract. Recent results on minimax robust time series interpolation and regression coefficient estimation are generalized and extended through a relationship with robust hypothesis testing. The spectral uncertainty classes in the time series problems are assumed to be convex and to satisfy an integral constraint such as on the variance of the process. It is shown that robust solutions in such cases can always be obtained from the least-favourable probability density functions for corresponding hypothesis testing problems. A specific class, the bounded spectral densities from the band model, is considered to illustrate the results.