Tests of the Null of Cointegration Using Integrated and Modified OLS Residuals
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This study develops a KPSS (Kwiatkowski et al., 1992)-type cointegration test utilizing residuals from integrated and modified ordinary least squares (IMOLS) estimation. The test statistic, denoted by KPSS^{Fb} has a pivotal null limit distribution under fixed-b assumption. The proposed test demonstrates reasonable performance in terms of size and power when the Andrews' AR(1) plug-in data-dependent (DD) bandwidth is employed and fixed-$b$ critical values are used. Additionally, two modified IMOLS residuals are proposed to obtain alternative data-dependent bandwidths. In the simulation experiment, these bandwidths deliver improved power properties for the proposed test.
Abstract
This study develops a KPSS (Kwiatkowski et al., 1992)-type cointegration test utilizing residuals from integrated and modified ordinary least squares (IMOLS) estimation. The test statistic, denoted by KPSS^{Fb} has a pivotal null limit distribution under fixed-b assumption. The proposed test demonstrates reasonable performance in terms of size and power when the Andrews' AR(1) plug-in data-dependent (DD) bandwidth is employed and fixed-$b$ critical values are used. Additionally, two modified IMOLS residuals are proposed to obtain alternative data-dependent bandwidths. In the simulation experiment, these bandwidths deliver improved power properties for the proposed test.
참고문헌 (17)
- Andrews, D. W. K., "Heteroskedasticity and autocorrelation consistent covariance matrix estimation", Econometrica, 59, pp.817~854 (1991)
- Caner, M., "Size distortions of tests of the null hypothesis of stationarity : Evidence and implications for the PPP debate", Journal of International Money and Finance, 20, pp.639~657 (2001)
- Cho, C. K., "Fixed-b inference for testing structural change in a time series regression", Econometrics, 5, pp.2~ (2017)
- Choi, I., "Testing for cointegration in a system of equations", Econometric Theory, 11, pp.952~983 (1995)
- Gabriel, V. J., "Tests for the null hypothesis of cointegration : A Monte Carlo comparison", Econometric Reviews, 22, pp.411~435 (2003)
- Hansen, B. E., "Efficient estimation and testing of cointegrating vectors in the presence of deterministic trends", Journal of Econometrics, 53, pp.87~121 (1992)
- Harris, D., "Non-stationary time series analysis and cointegration", pp.133~152 (1994)
- Kiefer, N. M., "A new asymptotic theory for heteroskedasticity-autocorrelation robust tests", Econometric Theory, 21, pp.1130~1164 (2005)
- Kwiatkowski, D., "Testing the null hypothesis of stationarity against the alternative of a unit root : How sure are we that economic time series have a unit root", Journal of Econometrics, 54, pp.154~178 (1992)
- M¨uller, U. K., "Size and power of tests of stationarity in highly autocorrelated time series", Journal of Econometrics, 128, pp.195~213 (2005)
- M¨uller, U. K., "HAC corrections for strongly autocorrelated time series", Journal of Business & Economic Statistics, 32, pp.311~322 (2014)
- Newey, W. K., "A simple, positive semi-definite, heteroskedasticity and autocorrelation consistent covariance matrix", Econometrica, 55, pp.703~708 (1987)
- Phillips, P. C. B., "Estimating long run economic equilibria", Review of Economic Studies, 58, pp.407~436 (1991)
- Phillips, P. C. B., "Spectral regression for cointegrated time series" (1988), Cowles Foundation for Research in Economics at Yale University
- Shin, Y., "A residual-based test of the null of cointegration against the alternative of no cointegration", Econometric Theory, 10, pp.91~115 (1994)
- Vogelsang, T. J., "Integrated modified OLS estimation and fixed-b inference for cointegrating regressions", Journal of Econometrics, 178, pp.741~760 (2014)
- Xiao, Z., "A CUSUM test for cointegration using regression residuals", Journal of Econometrics, 108, pp.43~61 (2002)