Abstract
A set of unit root tests are applied to test the existence of long-run real interest rate parity among the G-10 countries over the period 1971M1 to 2007M2. Rather than trusting the asymptotic distributions, this article uses simulation techniques to establish the small sample distributions of these tests, conditional on the stationary and nonstationary processes. The empirical results indicate that the tests have stable finite-sample sizes and higher size-adjusted powers such that the two estimated processes can be distinguished from each other. Thus, for six of the nine countries, their series are more likely to come from the estimated Autoregressive (AR) stationary process than from the nonstationary process. Noticeably, the testing results are rather different from those using the asymptotic distributions, in which only three countries support the real interest rate parity.
Notes
1 We thank the referee for this helpful comment.
2 The empirical literature related to long memory is briefly summarized as follows. Shea (Citation1991) found that allowing possibility of long memory significantly improves the performance of the model used. Lai (Citation1997) and Phillips (Citation1998) provided evidence that ex ante and ex post US real interest rates are fractionally integrated. Other papers dealing with fractional integration in interest rates include Tsay (Citation2000), Meade and Maier (Citation2003), Gil-Alana (Citation2004a, b) and Couchman et al. (Citation2006). We thank the referee for this helpful comment.