No label defined (Q3753322)

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 3990670
Language Label Description Also known as
default for all languages
No label defined
    English
    No label defined
    scientific article; zbMATH DE number 3990670

      Statements

      1986
      0 references
      multicollinearity
      0 references
      Durbin-Watson test
      0 references
      Shapiro-Wilk test
      0 references
      D'Agostino's test
      0 references
      generalized inverse regression
      0 references
      outliers
      0 references
      response surface
      0 references
      testing for normality
      0 references
      Box-Cox transformation
      0 references
      Ramsey's test
      0 references
      heteroscedasticity
      0 references
      serial correlation
      0 references
      multiple regression
      0 references
      least squares theory
      0 references
      data exploration
      0 references
      diagnostic checks
      0 references
      model selection
      0 references
      prediction
      0 references
      This monograph is written for those that have had a first course in regression and have some practical experience of multiple regression. After a review of least squares theory and data exploration in the first two chapters some algebraic and numerical problems involved in regression analysis are dealt with in Chapters 3-5. A study of diagnostic checks and plots are included in Chapters 6-9 while model selection and prediction are discussed in Chapters 10-12. In the final chapter alternatives to the usual assumptions about the errors are introductorily discussed. The first sentence in the preface reads ''Multiple regression analysis is one of the most used - and misused - statistical techniques, but elementary texts go little further than 'least squares theory' and residuals plotting''. I agree with this statement and conclude that it is important to publish texts that go beyond this and, in order to avoid further misuse of regression analysis, explain the philosophy and rationality of the technique. Unfortunately, also this elementary text fails to extend the usually published material: it takes a data analytic approach in which numerical precision is highlighted while interpretation of results, scientific model building and fundamental questions such as ''is this kind of analysis at all meaningful'' are ignored.
      0 references
      0 references
      0 references
      0 references
      0 references
      0 references
      0 references

      Identifiers

      0 references
      0 references
      0 references
      0 references