No label defined (Q3996232)
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 45877
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | No label defined |
scientific article; zbMATH DE number 45877 |
Statements
17 September 1992
0 references
linear models
0 references
0 references
This review can be summarized in a question: Why? The first ediition, truly a classic, was published in 1937. This edition was edited by a committee at Iowa State University. The publisher tanks David F. Cox for coordinating their work. Very few changes have been made vis-à-vis the seventh edition. The major change is the use of matrix notation in linear models. No consideration is given to the computer revolution and the ready availability of software to ease the burden of computation. Occasionally references are made to availability of software, but the impression left is that of writing at a time when only mainframes were available and user friendliness was not general. In fact, Section 3.6 on computers has been deleted, possibly as out of date. Little is done in the realm of the choice of sample size in spite of the fact that this can now be done accurately in a wide range of situations. This reviewer's joint work with \textit{Robert E. Odeh} [Sample-size choice. Charts for experiments with linear models. (1975; Zbl 0329.62064); 2nd ed. (1991)], for example, provides the solution for linear models. Levels of significance are always set at the magical.05 or.01 instead of by assessment of the convergence of the two actions. P-values are only mentioned as possible output in the brief comments on software. The editorial work in preparing this edition could have been more careful. A totally incorrect interpretation of confidence intervals (page 5) is carried forward from the Seventh Edition. Later (page 51, e.g.) the correct interpretation is used.
0 references