This is a volume of papers presented at a conference held at the University of North Carolina at Chapel Hill in May 2004. The conference commemorated the publication of Charles Spearman’s 1904 article on the structure of intelligence in which he used methods that eventually gave rise to the methods of factor analysis. The book consists of 15 papers presented at the conference covering developments in both the history and current methodology of factor analysis. The presenters are leading figures in the field of factor analysis. This makes the book an excellent resource for individual researchers using factor analysis, as well as a supplementary reading for graduate courses in factor analysis. Chapter 1, “Factor Analysis in the Year 2004: Still Spry at 100,” by Robert Cudeck, is a brief introduction to the chapters in the book. Cudeck himself presents a balanced and insightful historical view of the topic of factor analysis, noting its various methodological controversies and limitations, many of which are treated in the later chapters of the book. Chapter 2, “Three Faces of Factor Analysis,” by David J. Bartholomew, begins with a historical review of Spearman’s (1904) fundamental idea that “Whenever branches of intellectual activity are at all dissimilar, then their correlations with one another appear wholly due to their being all variants wholly saturated with some common fundamental Function (or group of Functions)” (p. 273). Bartholomew draws the statistical implications of this idea, involving concepts of partial correlation, Yule’s (1897) formulation of the true-and-error-score theory of reliability, and Spearman’s tetrad difference equation (which still is central to programs like TETRAD; Glymour, Scheines, Spirtes, & Kelly, 1987) which might be described roughly as programs for performing exploratory structural equation modeling). Bartholomew then contrasts Spearman’s single common factor theory with Thomson’s (1950) alternative model, which also successfully accounted for the pattern of correlations among intellectual variables having a single common factor in Spearman’s sense, as due to the variables’ being based on random samples from a huge population of latent neural bonds in the brain involved in the intellectual tasks measured. Bartholomew notes that implicit to Thomson’s model were several implausible
[1]
Stanley A. Mulaik,et al.
Comments on “the measurement of factorial indeterminacy”
,
1976
.
[2]
L. Thurstone.
The Vectors of Mind
,
1935
.
[3]
Louis Guttman,et al.
THE DETERMINACY OF FACTOR SCORE MATRICES WITH IMPLICATIONS FOR FIVE OTHER BASIC PROBLEMS OF COMMON‐FACTOR THEORY1
,
1955
.
[4]
Kevin T. Kelly,et al.
Discovering Causal Structure.
,
1989
.
[5]
Wm. R. Wright.
General Intelligence, Objectively Determined and Measured.
,
1905
.
[6]
C. B.,et al.
The Factorial Analysis of Human Ability
,
1939,
Nature.
[7]
K. Jöreskog.
Some contributions to maximum likelihood factor analysis
,
1967
.
[8]
C. Spearman.
The Abilities of Man their Nature and Measurement
,
2020,
Nature.
[9]
William Meredith,et al.
Latent curve analysis
,
1990
.
[10]
William Meredith,et al.
Notes on factorial invariance
,
1964
.
[11]
Mark Zegarelli.
Calculus II For Dummies
,
2008
.
[12]
G. Yule.
On the Theory of Correlation
,
1897
.
[13]
C. Spearman.
General intelligence Objectively Determined and Measured
,
1904
.
[14]
W. Meredith.
Measurement invariance, factor analysis and factorial invariance
,
1993
.
[15]
William Meredith,et al.
Rotation to achieve factorial invariance
,
1964
.