Gauss on least-squares and maximum-likelihood estimation (Q2144556)
From MaRDI portal
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Gauss on least-squares and maximum-likelihood estimation |
scientific article |
Statements
Gauss on least-squares and maximum-likelihood estimation (English)
0 references
14 June 2022
0 references
The article deals with Gauss' approach to least squares. It discusses Gauss' argumentation for normality of errors being necessary and sufficient for least squares formula yielding a maximal likelihood estimator in the linear model. In contrast to many previous discussions that found logical flaws in Gauss' approach, the author shows (by describing the main ideas of Gauss' arguments) that Gauss did not make the logical error of circular argument, but gradually improved his arguments, even if he never fully proved the claim.
0 references
history of statistics
0 references
least squares
0 references
normal distribution
0 references
arithmetic mean
0 references
