Abstract
A method is presented for evaluating the covariance matrix of a set of sequential forecasts obtained by regression analysis. The matrix can be used to derive the relation between the variance of the forecasts on the one hand, and the lead times between the forecasting time and the time at which the forecasted variables are realized, on the other hand. The determination of this relation is important whenever the optimal frequency of forecasting must be determined.
| Original language | English |
|---|---|
| Pages (from-to) | 121-132 |
| Number of pages | 12 |
| Journal | Journal of Statistical Planning and Inference |
| Volume | 5 |
| Issue number | 2 |
| DOIs | |
| State | Published - 1981 |
Keywords
- Errors of Forecasting
- First-Order Approximations
- Forecasts' Lead Times
- Maximum Likelihood Methods
- Variance of Forecasts
Fingerprint
Dive into the research topics of 'The covariance structure of sequential forecasts obtained by regression analysis'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver