Antonio Montañés

Testing for a Unit Root in Variables with a Double Change in the Mean

In this paper, we obtain a statistic that is useful for the analysis of the integration order of a variable which exhibits two changes in its mean. Our work begins by showing that the most commonly used unit root tests behave asymptotically in a correct manner for double changing mean variables. However, their use is not advisable in finite samples; rather, is better to design a new statistic which takes into account the presence of the two level shifts. We calculate the asymptotic distribution of this new statistic and tabulate it for several sample sizes using Monte Carlo methods. This new statistic allows us to show that the USA and UK real interest rates can be considered as stationary variables with a double shift in their mean.

Evidence of long-run purchasing power parity: analysis of real asian exchange rates in terms of the Japanese yen

Abstract In this paper we find strong new evidence in favour of the long-run purchasing power parity (PPP) hypothesis in the bilateral real exchange rates between the Japanese yen and the currencies of the most important southeast Asian economies only when the presence of several possible structural breaks of the series is taken into account. Such evidence for PPP is weaker for these southeast Asian exchange rates with the US dollar, the German mark and the Australian dollar.

The European Union currencies and the US dollar: from post-Bretton-Woods to the Euro

Abstract In this paper we study the evolution of the US dollar real exchange rate vis-a-vis the European Union currencies in the floating post-Bretton-Woods era, both before and after the birth of the Euro. In the first period we find that most of the persistence shown by this rate is due to the movements of the US dollar during the mid-1980s. Once these effects are isolated, we can conclude that the US dollar real exchange rate exhibits stationarity with those currencies that are closely linked to the German Mark. However, when we include the observations covering the period during which the Euro was created, we cannot reject the unit root null hypothesis for any currency.

Measurement errors and outliers in seasonal unit root testing

Seasonal and non-seasonal data are frequently observed with noise. For instance, the time series can have irregular abrupt changes and interruptions following as a result of additive or temporary change outliers caused by external circumstances. Equally, the time series can have measurement errors. In this paper we analyse the above types of data irregularities on the behavior of seasonal unit root tests. Outliers and measurement errors can seriously affect seasonal unit root inference and it is shown how the distortion of the tests will depend upon the frequency, magnitude, and persistence of the outliers as well as on the signal to noise ratio associated with measurement errors. Some solutions to the implied inference problems are suggested and shown to work in practice.

The asymptotic behaviour of the Dickey-Fuller tests under the crash hypothesis

This paper considers the behaviour of the Dickey-Fuller tests when the variable being studied is generated according to Perrons (1989) crash hypothesis. We show that these statistics tend towards the Dickey-Fuller distributions under the null hypothesis and diverge towards -[infinity] under the alternative.

Level shifts, unit roots and misspecification of the breaking date

Abstract This paper analyses the asymptoric behaviour of the Perron (1990) unit root tests in the presence of an erroneous location of the breaking date. It is analytically proved that these statistics converge to their correct distribution under the null hypothesis and diverge to −∞ to under the alternative.

THE BEHAVIOR OF HEGY TESTS FOR QUARTERLY TIME SERIES WITH SEASONAL MEAN SHIFTS

ABSTRACT This paper studies the behavior of the HEGY statistics for quarterly data, for seasonal autoregressive unit roots, when the analyzed time series is deterministic seasonal stationary but exhibits a change in the seasonal pattern. We analyze also the HEGY test for the nonseasonal unit root. the data generation process being trend stationary too. Our results show that when the break magnitudes are finite, the HEGY test statistics are not asymptotically biased toward the nonrejection of the seasonal and nonseasonal unit root hypotheses. However, the finite sample power properties may be substantially affected, the behavior of the tests depending on the type of the break.

Real exchange rates and structural breaks: evidence for the Spanish peseta

This paper analyses the fulfilment of the long-run PPP hypothesis between the Spanish Peseta and the currencies of the most important trade partners of the Spanish Economy. We show that the bilateral real exchange rate of the Spanish Peseta can be characterized as being stationary around a mean which exhibits some changes in its evolution.

Structural breaks, unit roots and methods for removing the autocorrelation pattern

This paper examines the asymptotic and finite sample behaviour of the ADF and Phillips-Perron statistics under the presence of a break in the trend function. We prove that the break magnitude affects these two statistics in a similar way, drawing them closer the acceptance zone, the higher the break magnitude. By contrast, the influence of the lag truncation parameter does not have a similar effect on them, being very important for the ADF whilst negligible for the Phillips-Perron statistics.

Are the consumption/output and investment/output ratios stationary? An international analysis

This paper analyses the integration order of the consumption/output and investment/output ratios for a group of the most important OECD countries. Results show that these ratios can exhibit some structural breaks. Thus, the use of those statistics which do not take into account the presence of breaks leads to the acceptance of the unit root null hypothesis. A clear increase in the number of rejections of the unit root null hypothesis is found when these structural breaks are included in the model specification.