✦ LIBER ✦
The correlation structure of the sample autocovariance function for a particular class of time series with elliptically contoured distribution
✍ Scribed by Marc G. Genton
- Publisher
- Elsevier Science
- Year
- 1999
- Tongue
- English
- Weight
- 375 KB
- Volume
- 41
- Category
- Article
- ISSN
- 0167-7152
No coin nor oath required. For personal study only.
✦ Synopsis
In the context of time series, the classical estimator of the autocovariance function can be written as a quadratic form of the observations. If data have an elliptically contoured distribution with constant mean, then the correlation between the sample autocovariance function at two different lags is a function of the time design matrix and the covariance matrix of the process. When data have a regular support, an explicit formula for this correlation is available for a particular family of covariance matrices. Surprisingly, this correlation structure is exactly the same as the one for a Gaussian white noise.