Abstract
A new kernel for estimating long-run variances of stationary seasonal time series is proposed. The proposed kernel has an oscillating pattern which is in harmony with that of the autocovariance functions of seasonal time series. A Monte-Carlo experiment shows that the estimator based on the proposed kernel outperforms estimators based on existing kernels such as the Bartlett kernel, Parzen kernel, and Turkey-Hanning kernel for two typical monthly time series processes with moderate autocorrelations.
Original language | English |
---|---|
Pages (from-to) | 165-171 |
Number of pages | 7 |
Journal | Economics Letters |
Volume | 76 |
Issue number | 2 |
DOIs | |
State | Published - Jul 2002 |
Keywords
- Autocovariance function
- Efficiency
- Seasonality