Peter Schonemann

Peter H. Schönemann is a German born psychometrician and statistical expert. He is Professor Emeritus in the Department of Psychological Sciences at Purdue University. His research interests include multivaritate statistics, multidimensional scaling and measurement, quantitative behavior genetics, test theory and mathematical tools for social scientists. He has published roughly 90 papers dealing mainly with the subjects of psychometrics and mathematical scaling. Schönemann’s influences include Louis Guttman, Lee Cronbach, Oscar Kempthorne and Henry Kaiser.

Schönemann has also been a persistent critic of what he considers to be scientifically sanctioned racism in psychology. In particular, he claims that (1) Arthur Jensen and others routinely confuse the first principal component (PC1) with g as Charles Spearman defined it, and that (2) the high IQ heritability estimates reported in the literature derive from restrictive formal models whose underlying assumptions are rarely tested and usually violated by the data.^{[1][2] [3]}

Additional recommended knowledge

Safe Weighing Range Ensures Accurate Results

Guide to balance cleaning: 8 simple steps

Essential Laboratory Skills Guide

Education

1953-56 University of Munich (Vordiplom)

1956-59 University of Gottingen (Diplom)

1960-64 University of Illinois (Ph.D. in General Psychology)

Notable work

Schönemann's PhD thesis "A solution of the orthogonal Procrustes problem with applications to orthogonal and oblique rotation," proposed a solution to the orthogonal Procrustes problem. Other Schönemann papers include "A generalized solution of the orthogonal Procrustes problem",^[4] "The minimum average correlation between equivalent sets of uncorrelated factors",^[5] and "Some new results on factor indeterminacy" ^[6] co-authored with M.M. Wang. All papers are routinely cited in the psychometric literature.^[7][8][9] Schönemann has also written numerous book chapters, including his most recent "Psychometrics of Intelligence" chapter in the Encyclopedia of Social Measurement and the “Heritability” chapter in the “Encyclopedia of Human Intelligence”.^[10]

g theory

Schönemann, in line with authors Louis Guttman and Lee Cronbach, argues for the non-existence of psychometric g.^[11][12][13] He writes that there is a fundamental difference between g, first defined by Charles Spearman as a latent one-dimensional variable that accounts for all correlations among any intelligence tests, and a first principal component (PC1) of a positive correlation matrix. Spearman's tetrad difference equation states a necessary condition for such a g to exist.^[14] The important proviso for Spearman's claim that such a g qualifies as an "objective definition" of "intelligence", is that all correlation matrices of "intelligence tests" must satisfy this necessary condition, not just one or two, because they are all samples of a universe of tests subject to the same g. Schönemann and others argue that this condition is routinely violated by all correlation matrices of reasonable size, and thus, such a g does not exist.^[15].

Twin Studies

Schönemann, in a number of publications, has argued that the statistical heritability estimates used for most twin studies rest on restrictive assumptions which are usually not tested, and if they are, are often found to be violated by the data.^[16] This is true for the monozygotic twins raised apart vs together (MZT) studies (Burt, Shields, Jinks and Fulker, Bouchard) as well as for the more widely used MZT vs dizygotic twins raised together studies.^[17] For example, the narrow heritabilities of responses to the question “did you have your back rubbed” work out to .92 heritable for males and .21 heritable for females. Using the statistical models published in Loehlin and Nichols (1976) the question “Did you wear sunglasses after dark?” is 130% heritable for males and 103% for females. ^{[18] [19]}

Several other scholars have also criticized heritability estimates,^{[20][21] [22]} and twin studies.^{[23][24][25][26][27]} Yet others argue that the problem with heritability is "a station passed" and that behavior geneticists can and should concentrate on more important problems.^[28]

References

• Power Tables for Analysis of Variance

• Alternative measures of fit for the Schönemann-carroll matrix fitting algorithm

• Complexity, extremity, and affect in male and female judgments