The Effect of Data Transformation on Common Cycle, Cointegration, and Unit Root Tests: Monte Carlo Results and a Simple Test

In the conduct of empirical macroeconomic research, unit root, cointegration, common cycle, and related tests statistics are often constructed using logged data, even though there is often no clear reason, at least from an empirical perspective, why logs should be used rather than levels. Unfortunately, it is also the case that standard data transformation tests, such as those based on the Box-Cox transformation, cannot be shown to be consistent unless an assumption is made concerning whether the series being examined is I(0) or I(1), so that a sort of circular testing problem exists. In this paper, we address two quite different but related issues that arise in the context of data transformation. First, we address the circular testing problem that arises when choosing data transformation and the order of integratedness. In particular, we propose a simple randomized procedure, coupled with sample conditioning, for choosing between levels and log-levels specifications in the presence of deterministic and/or stochastic trends. Second, we note that even if pre-testing is not undertaken to determine data transformation, it is important to be aware of the impact that incorrect data transformation has on tests frequently used in empirical works. For this reason, we carry out a series of Monte Carlo experiments illustrating the rather substantive effect that incorrect transformation can have on the finite sample performance of common feature and cointegration tests. These Monte Carlo findings underscore the importance of either using economic theory as a guide to data transformation and/or using econometric tests such as the one discussed in this paper as aids when choosing data transformation.

[1]  Farshid Vahid,et al.  Common Trends and Common Cycles , 1993 .

[2]  Philip Hans Franses,et al.  Testing for Smooth Transition Nonlinearity in the Presence of Outliers , 1996 .

[3]  P. Franses,et al.  Testing for Unit Roots and Nonlinear Transformations , 1998 .

[4]  Farshid Vahid,et al.  Common cycles and the importance of transitory shocks to macroeconomic aggregates (revised version) , 1998 .

[5]  Ernst Eberlein,et al.  On Strong Invariance Principles Under Dependence Assumptions , 1986 .

[6]  A. Inoue.  TESTING FOR DISTRIBUTIONAL CHANGE IN TIME SERIES , 2001, Econometric Theory.

[7]  Peter C. B. Phillips,et al.  Nonlinear Regressions with Integrated Time Series , 2001 .

[8]  Helmut Lütkepohl,et al.  Modified wald tests under nonregular conditions , 1997 .

[9]  Charles I. Plosser,et al.  Real Business Cycles , 1983, Journal of Political Economy.

[10]  Peter C. B. Phillips,et al.  ASYMPTOTICS FOR NONLINEAR TRANSFORMATIONS OF INTEGRATED TIME SERIES , 1999, Econometric Theory.

[11]  W. Fuller,et al.  Distribution of the Estimators for Autoregressive Time Series with a Unit Root , 1979 .

[12]  Clive W. J. Granger,et al.  NONLINEAR TRANSFORMATIONS OF INTEGRATED TIME SERIES , 1991 .

[13]  R. Rasche,et al.  Stochastic trends and economic fluctuations in a large open economy , 1998 .

[14]  P. Franses,et al.  Forecasting power-transformed time series data , 1999 .

[15]  Data Transformation and Forecasting in Models with Unit Roots and Cointegration , 2001 .

[16]  Bruce E. Hansen,et al.  Inference When a Nuisance Parameter Is Not Identified under the Null Hypothesis , 1996 .

[17]  M. McAleer,et al.  ANALYTICAL POWER COMPARISONS OF NESTED AND NONNESTED TESTS FOR LINEAR AND LOGLINEAR REGRESSION MODELS , 1999, Econometric Theory.

[18]  M. McAleer,et al.  Tests of linear and logarithmic transformations for integrated processes , 1999 .

[19]  J. Stock,et al.  Interpreting Evidence on Money-Income Causality , 1987 .

[20]  Michael P. Clements,et al.  On winning forecasting competitions in economics , 1999 .