No label defined (Q3332098)
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 3864319
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | No label defined |
scientific article; zbMATH DE number 3864319 |
Statements
1983
0 references
mean consistency
0 references
conditional distribution
0 references
linear model
0 references
least squares estimate
0 references
convergence rates
0 references
0.8951587677001953
0 references
Consider the linear model \(y_ i=\beta_ 1X_{i1}+...+\beta_ px_{ip}+e_ i (i=1,2,...)\) where \(x_{ij}\) are known constants, \(\beta_ 1,...,\beta_ p\) are unknown parameters, and \(e_ i\) are random errors. Denote \(\beta =(\beta_ 1,...,\beta_ p)^ t\), \(X_ n=(x_{ij})_{n\times p}\). Let \(b_ n=(b_{n1},...,b_{np})^ t\) be the least squares estimate of \(\beta\) based on the design matrix \(X_ n\) and \((y_ 1,...,y_ n)^ t.\) In this paper, a sufficient condition on \(\lim_{n\to \infty} E\| b_ n-\beta \|^ r=0\) for some \(r\in(0,2]\) is given, and convergence rates are obtained. These results improve those of \textit{X. Chen}, Acta Math. Sin. 24, 36-44 (1981; Zbl 0473.62051).
0 references