No label defined (Q3716151)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 3945194
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | No label defined |
scientific article; zbMATH DE number 3945194 |
Statements
1985
0 references
autoregressive processes
0 references
time series
0 references
missing value
0 references
best linear forward and backward extrapolations
0 references
best linear interpolation
0 references
residual variances
0 references
stationary
0 references
non-stationary
0 references
covariance function
0 references
0.8141882419586182
0 references
0.7965020537376404
0 references
0.7836262583732605
0 references
0.7741649746894836
0 references
[For the entire collection see Zbl 0583.00028.] Consider a time series \(\{X_ t\}\) with a missing value \(X_ m\). Denote by \(\hat X_ m\) and \(\tilde X_ m\) the best linear forward and backward extrapolations of \(X_ m\), respectively. Let \(X^*\!_ m\) be the best linear combination of \(\hat X_ m\) and \(\tilde X_ m\) for the approximation of \(X_ m\) and let \(X^ 0_ m\) be the best linear interpolation. The residual variances \(\lambda^ 2_ m=E(X_ m-X^*\!_ m)^ 2\) and \(\tau^ 2_ m=E(X_ m-X^ 0_ m)^ 2\) are compared in the case that \(\{X_ t\}\) is a stationary or a non-stationary AR(2) process. Explicit formulas for the covariance function of non-stationary AR(2) processes are also derived.
0 references