Fitting Equations to Data: Computer Analysis of Multifactor Data

ISBN-13: 9780471376842 / Angielski / Miękka / 1999 / 458 str.

Cuthbert Daniel; Fred S. Wood; Fred S. Wood

Opis

This revised and updated volume describes methods which are now a fundamental part of the theory and explanation of data analysis. This edition includes numerous extensions and devices such as component and component-plus residual plots, cross-verification with a second sample and an index of required x-precision. The methods described have been applied to agricultural, environmental, management, marketing, medical, physical and social science studies. This work also provides a historical insight into how computer technology has come to be used in data processing and analysis.

Recenzje

"...a grand historical document for industrial statistics in its glory days, as its selection for the Classics Library implies." ––Technometrics Vol. 42, No. 4 May 2001

This book provides an excellent insight into the minds of two master craftsmen at work. I very much applaud the decision to include this in a "classics library" and would encourage more authors to produce statistics books in the same vein, i.e. focused on the practical application of the subject rather than methodology development. Anyone involved in the analysis of unbalanced multifactor dtaa will find this book an extremely useful source of practical advice. ––The Statistician 50 (1) 2001.

Spis treści

Assumptions and Methods of Fitting Equations.

One Independent Variable.

Two or More Independent Variables.

Fitting an Equation in Three Independent Variables.

Selection of Independent Variables.

Some Consequences of the Disposition of the Data Points.

Selection of Variables in Nested Data.

Nonlinear Least Squares, a Complex Example.

Glossary.

User′s Manual.

Bibliography.

Index.

Blurb

Helps any serious data analyst with a computer to recognize the strengths and limitations of data, to test the assumptions implicit in the least squares methods used to fit the data, to select appropriate forms of the variables, to judge which combinations of variables are most influential, and to state the conditions under which the fitted equations are applicable. This edition includes numerous extensions and new devices such as component and component–plus–residual plots, cross verification with a second sample, and an index of required x–precision; also, the search for better subset equations is enlarged to cover 262,144 alternatives. The methods described have been applied in agricultural, environmental, management, marketing, medical, physical, and social sciences. Mathematics is kept to the level of college algebra.