Spurious Multivariate Regressions Under Fractionally Integrated Processes
Abstract
This article studies spurious regression in the multivariate case for any finite number of fractionally integrated variables, stationary or not. We prove that the asymptotic behavior of the estimated coefficients and their t-statistics depend on the degrees of persistence of the regressors and the regressand. Nonsense inference could therefore be drawn when the sum of the degrees of persistence of the regressor and regressand is greater than or equal to 1/2. Moreover, the asymptotic behavior from the most persistent regressor spreads to correlated regressors. Thus, the risk of uncovering spurious results increases as more regressors are included. Inference drawn from other test statistics such as the joint F-test, the R-squared, and the Durbin-Watson is also misleading. Finite sample evidence supports our findings.
Download
The version of record can be downloaded here, while the accepted version can be freely downloaded here
Recommended citation
Ventosa-Santaulària, D., Vera-Valdés, J.E., Lasak, K., and Ramírez-Vargas, R. (2020). “Spurious Multivariate Regressions Under Fractionally Integrated Processes.” Communications in Statistics - Theory and Methods. 51(7). DOI: 10.1080/03610926.2020.1758945
@article{VentosaSantaularia2020,
author = {Ventosa-Santaulària, D. and Vera-Valdés, J.E. and Lasak, K. and Ramírez-Vargas, R.},
title = {Spurious Multivariate Regressions Under Fractionally Integrated Processes},
journal = {Communications in Statistics - Theory and Methods},
volume = {51},
number = {7},
pages = {2034-2056},
doi = {https://doi.org/10.1080/03610926.2020.1758945},
url = {https://www.tandfonline.com/doi/full/10.1080/03610926.2020.1758945},
year = {2020}
}