A universe of infinitely many quantitative variables is considered, from which a sample ofn variables is arbitrarily selected. Only linear least-squares regressions are considered, based on an infinitely large population of individuals or respondents. In the sample of variables, the predicted value of a variablex from the remainingn − 1 variables is called the partial image ofx, and the error of prediction is called the partial anti-image ofx. The predicted value ofx from the entire universe, or the limit of its partial images asn → ∞, is called the total image ofx, and the corresponding error is called the total anti-image. Images and anti-images can be used to explain “why” any two variablesx j andx k are correlated with each other, or to reveal the structure of the intercorrelations of the sample and of the universe. It is demonstrated that image theory is related to common-factor theory but has greater generality than common-factor theory, being able to deal with structures other than those describable in a Spearman-Thurstone factor space. A universal computing procedure is suggested, based upon the inverse of the correlation matrix.
KeywordsPublic Policy Large Population Correlation Matrix Statistical Theory Quantitative Variable
Unable to display preview. Download preview PDF.
- 1.Guttman, Louis. A note on the derivation of formulae for multiple and partial correlation.Ann. math. Statist., 1938,9, 305–308.Google Scholar
- 2.Guttman, Louis. Multiple rectilinear prediction and the resolution into components.Psychometrika, 1940,5, 75–99.Google Scholar
- 3.Guttman, Louis, and Cohen, Jozef. Multiple rectilinear prediction and the resolution into components: II.Psychometrika, 1943,8, 169–183.Google Scholar
- 4.Guttman, Louis. Review of Thurstone'sMultiple-factor analysis. J. Amer. statist. Ass., 1947,42, 651–656.Google Scholar
- 5.Guttman, Louis. The Israel alpha technique for scale analysis: a preliminary statement (stenciled). The Israel Institute of Applied Social Research, Jerusalem, Israel, 1951.Google Scholar
- 6.Guttman, Louis. The theory of nodular structures. (In preparation)Google Scholar
- 7.Guttman, Louis. A new approach to factor analysis: The Radex. In Paul F. Lazarsfeld, Mathematical thinking in the social sciences. New York: Columbia Univ. Press, 1953.Google Scholar
- 8.Guttman, Louis. The matrices of least-squares image analysis. (In preparation)Google Scholar
- 9.Guttman, Louis. The existence of total least-squares images and anti-images (In preparation)Google Scholar
- 10.Guttman, Louis. A reanalysis of factor analysis. (In preparation)Google Scholar
- 11.Jackson, Dunham. The trigonometry of correlation.Amer. math. Monthly, 1924,31, 275–280.Google Scholar
- 12.Thurstone, L. L. Multiple-factor analysis. Chicago: Univ. Chicago Press, 1947.Google Scholar