Semiparametric Frequency Domain Analysis of Fractional Cointegration - (Revised Version Forthcoming in P M Robinson: Time Series with Long Memory (Oxford University Press).
LSE STICERD Research Paper No. EM348
1998
- 494Usage
Metric Options: CountsSelecting the 1-year or 3-year option will change the metrics count to percentiles, illustrating how an article or review compares to other articles or reviews within the selected time period in the same journal. Selecting the 1-year option compares the metrics against other articles/reviews that were also published in the same calendar year. Selecting the 3-year option compares the metrics against other articles/reviews that were also published in the same calendar year plus the two years prior.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Paper Description
The concept of cointegration has principally been developed under the assumption that the raw data vector zt is I(1) and the cointegrating residual et is I(0), but is also of interest in more general, including fractional, circumstances, where zt is stationary with long memory and et is stationay with less memory, or where zt is nonstationary while et is either less nonstationay or stationary, possibly with long memory. Inference rules based on estimates of the cointegrating vector that have been developed in the I(1) / I(0) case appear to lose validity in the above circumstances, while the estimates themselves, including ordinary least squares, are typically inconsistent when zt is stationary. Partitioning zt into a scalar yt and vector xt , we consider a narrow-band frequency domain least squares estimate of yt on xt . This estimate is consistent under stationary zt , whereas least squares is inconsistent due to correlation between xt and et . This correlation does not prevent consistency of least squares when zt is nonstationary, but it produces a larger second order bias relative to the frequency domain estimate in the I(1) / I(0) case, and a slower rate of convergence in many circumstances in which zt exhibits less-than-I(1) nonstationarity. When et is itself nonstationary, the two estimates have a common limit distribution. Our conclusions in the I(1) / I(0) case are supported by Monte Carlo simulations. A semiparametric methodology for fractional cointegration analysis is applied to data analysed by Engle and Granger (1987) and Campbeell and Shiller (1987).
Bibliographic Details
Provide Feedback
Have ideas for a new metric? Would you like to see something else here?Let us know