No label defined (Q4531263)
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 1747147
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | No label defined |
scientific article; zbMATH DE number 1747147 |
Statements
29 May 2002
0 references
asymptotic properties
0 references
0.7553548812866211
0 references
0.7423602342605591
0 references
0.7342351675033569
0 references
The regression model \(E(\mathbf y)=\eta (\theta)\), where the mean is a vector function of the parameter \(\theta \in \Theta \subset \mathbf R^m\), is said to be locally regular in \(\theta\) if the matrix of the partial derivatives \[ \partial \eta (\theta)=(\partial \eta _i(\theta)/\partial \theta _j) \] has rank \(m\). If this model is locally regular in every point of the parameter space, then it is called globally regular. The subject of the paper are the regression models \[ E(y_i)=g({\mathbf x}_i^T\theta),\quad i=1,\dots ,n. \] In the case that the vectors \(\mathbf x_i\) are random, the presented general sufficient conditions guarantee the local regularity almost surely for \(n\geq m\), and conditions for the asymptotic global regularity are also included. Conditions implying that in this random setting the model is globally regular almost surely for \(n\geq 2m\) are also presented.
0 references