Methods of correlation analysis.
Eine sehr ausführlich gehaltene Darstellung der Korrelationsrechnung. Was das Buch an über die bisher angewendeten Methoden Hinausgehendem enthält, geht, wie Verf. im Vorwort mitteilt, zurück auf die Untersuchungen einer Reihe junger Forscher des Bureau of Agricultural Economics of the United States Department of Agriculture. Hier ist zu nennen die Anwendung der \textit{Doolittle}-Methode auf Probleme der Mehrfachkorrelation, die Entwicklung von Näherungsverfahren und raschen graphischen Methoden zur Bestimmung nichtlinearer Mehrfachkorrelationen, die Entwicklung von Methoden zur Behandlung der verbundenen Korrelationen, schließlich die ausgedehnte Anwendung dieser Methoden bei aktuellen Untersuchungen -- zugleich der konkrete Nachweis der Anwendungsmöglichkeiten in der Forschung. Ferner wurden die von \textit{``Student} und \textit{R. A. Fisher} in den letzten Jahrzehnten entwickelten Theorien zur Beurteilung der Zuverlässigkeit von Schlüssen dargestellt. Aus dem Inhaltsverzeichnis: Measuring the variability of a statistical series (Chap. 1, p. 1-12). Judging the reliability of statistical results (Chap. 2, p. 13-26). The relation between two variables, and the idea of function (Chap. 3, p. 27-39). Determining the way one variable changes when another changes (1) by the use of averages (Chap. 4, p. 40-50), (2) according to the straight-line function (Chap. 5, p. 51-64), (3) for curvilinear functions (Chap. 6, p. 65-110). Measuring accuracy of estimate and degree of correlation (Chap. 7, p. 111-124). Practical methods for working two-variable correlation problems (Chap. 8, p. 125-135). Three measures of correlation; the meaning and use for each (Chap. 9, p. 136-138). Determining the way on variable changes when two or more variables change (1) by successive elimination (Chap. 10, p. 139-151), (2) by cross-classification and averages (Chap. 11, p. 152-157), (3) by using a linear regression equation (Chap. 12, p. 158-173). Measuring accuracy of estimate and degree of correlation for linear multiple correlation (Chap. 13, p. 174-186). Determining the way one variable changes when two or more other variables change (3) using curvilinear regressions (Chap. 14, p. 187-219). Measuring accuracy of estimate and degree of correlation for curvilinear multiple correlation (Chap. 15, p. 220-228). Short-cut methods of determining net regression lines and curves (Chap. 16, p. 229-241). Measuring the way a dependant variable changes with changes in a non-quantitative independent factor (Chap. 17, p. 242-250). Determining the reliability of correlation conclusions (Chap. 18, p. 251-264). Influence of selection of sample and accuracy of observations on correlation results (Chap. 19, p. 265-276). Measuring the relation between one variable and two or more others operating jointly (Chap. 20, p. 277-299). Supplementary methods for determining curvilinear and joint relations (Chap. 21, p. 300-317). Types of problems to which correlation analysis has been applied (Chap. 22, p. 318-340). Steps in research work, and the place of statistical analysis (Chap. 23, p. 341-352). Appendix 1: Methods of computation (p. 353-369). 2: Technical notes (p. 370-390). 3: Graphic charts for interpreting or adjusting correlation constants (p. 391-398). 4: List of important equations (p. 399-404). 5: Glossary (p. 405), References (p. 406), Index (p. 407-427). Besprechung: L. R. C.; Journal Royal Statistical Soc. 64 (1931), 302-303.
This page was built for publication: Methods of correlation analysis.
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5917083)
