No label defined (Q3218586)
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 3884710
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | No label defined |
scientific article; zbMATH DE number 3884710 |
Statements
1983
0 references
Adaptive approximation techniques
0 references
exponential families
0 references
cross-validation technique
0 references
Akaike information criterion
0 references
0.7700928449630737
0 references
0.746296763420105
0 references
[For the entire collection see Zbl 0533.00014.] Adaptive approximation techniques are needed when approximating discrete sets of points. Most useful approximating sets of functions are splines, and their multivariate extensions, also exponential families. The question, which is considered here, is, what criteria can be used to determine how smooth we need to approximate the data so that the residuals of the approximation are the errors in the data values? Three methods are presented. The first comparing the unit-lag auto-correlation of the sequence of residuals for subsequent approximations. The second utilizes the generalized cross-validation technique, while the third uses information theoretic criteria to arrive at the Akaike information criterion.
0 references