In introducing the founders, Jones noted that the first organizational meeting of the Society occurred in February of 1935 and the first professional meeting occurred in September 1935, in connection with the convention of the American Psychological Association. In the Psychometric Society's first year, the president was L. L. Thurstone, the secretary was Paul Horst, the treasurer was Jack Dunlap, and the chairman of the membership committee was John Stalnaker. The editorial council consisted of Thurstone, chairman, Horst and Albert Kurtz, editors, and Marion Richardson, managing editor. The editorial board was noteworthy for its great breadth of interest, and its international and multidisciplinary character.

The purpose of the Psychometric Society is to encourage mathematical psychology. This article justifies the emphasis on quantification, and upon rationalization in science, as well as the Society's conception of the fundamental nature of science.

On the occasion of Psychometrika's fiftieth anniversary, the past twenty-five years' developments in mental test theory are reviewed, with special emphasis on the topics receiving attention in the pages of this journal. (Analogous reviews for Psychometrika's first quarter century were given by Gulliksen and Guilford in 1961.) Much of the recent progress in test theory (and in other branches of psychometrics as well) has been made by treating the problems in this field as being essentially ones of statistical inference. It is concluded that (a) research in test theory is in a healthy state and (b) Psychometrika is an important source of information about that research.

Papers on factor analysis appearing in Psychometrika reflect the initial efforts of the Thurstonians to reformulate psychology as a quantitative science. The Thurstonians' emphasis on the development of factor analysis as an exploratory methodology was not new with them but was taken from British statisticians and psychologists who preceded them, whose literature the Thurstonians otherwise tended to ignore. The Thurstonians' rejection of general factors and focus on rotation to simple structure reflected an attempt to avoid statistical artifact and to identify factors with psychological substance. Much of the literature on factor analysis in Psychometrika concerned solving technical problems in the exploratory factor analysis method. Factor analysis took a major shift in direction in the 1970's with the development of confirmatory methodologies, many of which now receive greater attention than the method of exploratory factor analysis, most of the problems of which are now resolved.

The field of linear structural equation modeling with continuous variables is reviewed. Trends in psychometric theory and data analysis across the five decades of publication of Psychometrika are discussed, especially the clarification of concepts of population and sample, explication of the parametric structure of models, delineation of concepts of exploratory and confirmatory data analysis, expansion of statistical theory in psychometrics, estimation via optimization of an explicit objective function, and implementation of general function minimization methods. Developments in the ideas of factor analysis, latent variables, as well as structural and causal modeling are noted. Some major conceptual achievements involving general covariance structure representations, multiple population models, and moment structures are reviewed. The major statistical achievements of normal theory generalized least squares estimation, elliptical and distribution-free estimation, and higher-moment estimation are discussed. Computer programs that implement some of the theoretical developments are described.

Approximately 15% of all papers appearing in Psychometrika during the period 1960–1984 have been statistical or data analytic in nature. While these papers cover a very wide range of issues and are technically quite similar to those appearing in other major statistical journals, collectively they possess features which make them identifiably Psychometrika.

Progress over the past twenty-five years in the development and improvement of models for representation of similarity data is reviewed. The discussion includes comments on class, dimensional, ideal type, and dichotomous attribute representations of underlying similarity structures. Most of the theoretical research in the area appeared, and continues to appear, in Psychometrika.

Mathematical models have been represented in Psychometrika first in biophysics, then in stochastic models of behavior, and later in computer simulations of behavior. Other specialized journals now attract many articles in these areas, but Psychometrika's policy of broad interest in all aspects of quantitative psychology remains sound. This paper reviews Psychometrika's coverage of mathematical models and computation, and discusses some matters of editorial policy.

This paper discusses the compatibility of the polychotomous Rasch model with dichotomization of the response continuum. It is argued that in the case of graded responses, the response categories presented to the subject are essentially an arbitrary polychotomization of the response continuum, ranging for example from total rejection or disagreement to total acceptance or agreement of an item or statement. Because of this arbitrariness, the measurement outcome should be independent of the specific polychotomization applied, for example, presenting a specific multicategory response format should not affect the measurement outcome. When such is the case, the original polychotomous model is called “compatible” with dichotomization.

A distinction is made between polychotomization or dichotomization “before the fact,” that is, in constructing the response format, and polycho- or dichotomization “after the fact,” for example in dichotomizing existing graded response data.

It is shown that, at least in case of dichotomization after-the-fact, the polychotomous Rasch model is not compatible with dichotomization, unless a rather special condition of the model parameters is met. Insofar as it may be argued that dichotomization before the fact is not essentially different from dichotomization after the fact, the value of the unidimensional polychotomous Rasch model is consequently questionable. The impact of our conclusion on related models is also discussed.

A direct method in handling incomplete data in general covariance structural models is investigated. Asymptotic statistical properties of the generalized least squares method are developed. It is shown that this approach has very close relationships with the maximum likelihood approach. Iterative procedures for obtaining the generalized least squares estimates, the maximum likelihood estimates, as well as their standard error estimates are derived. Computer programs for the confirmatory factor analysis model are implemented. A longitudinal type data set is used as an example to illustrate the results.

A statistical model for interpreting psychological scaling research, based on the heuristic work of Reynolds (1983), is developed. This new approach has certain advantages over the standard property fitting approach (Chang and Carroll, 1969) currently used to interpret multidimensional scaling spaces (Shepard, 1962; Torgerson, 1965). These advantages are (a) the ability to directly assess the correspondence of a descriptor vector(s) to a symmetric matrix, and (b) to provide a method in which only ordinal properties of such descriptors are required: thus standard rating, ranking, or sorting data collection methods can be used as the basis to interpret the multidimensional space resulting from the distance data.

This paper considers a multivariate normal model with one of the component variables observable only in polytomous form. The maximum likelihood approach is used for estimation of the parameters in the model. The Newton-Raphson algorithm is implemented to obtain the solution of the problem. Examples based on real and simulated data are reported.

Statistical methods are presented to facilitate a more complete analysis of results obtained when a scaling model is applied to data from two or more groups. These methods can be used to (a) compare the corresponding estimated latent distributions obtained using the scaling model applied to the different groups, (b) compare the corresponding estimated item reliabilities (or item response error rates) for the different groups, and (c) test whether the scaling model applied to the several groups can be replaced by a more parsimonious scaling model that includes various homogeneity constraints (i.e., constraints that describe which parameters in the model are the same for the several groups). Various kinds of scaling models are considered here in the multiple-group context.

True score tolerance intervals, which are designed to cover a chosen proportion of the conditional distribution of true scores given an observed score, are suggested as alternatives to true score confidence intervals. Using large sample theory, a tolerance interval estimator for the beta binomial is derived. An example indicates that with moderate sample sizes, tolerance intervals with high probability of coverage will not be much wider than when the two beta true score parameters are known.

Jöreskog (1974) developed a latent variable model for the covariance structure of the circumplex which, under certain conditions, includes a model for a patterned correlation matrix (Browne, 1977). This model is of limited usefulness, however, in that it employs a known matrix that is rank deficient for many problems. Furthermore, the model is inappropriate for the circumplex which contains negative covariances. This paper presents alternative models for the perfect circumplex and quasi-circumplex that avoids these difficulties, and that includes the important model for a patterned correlation circumplex matrix. Two numerical examples are provided.

In this note we derive an upper bound for the minimum for the multidimensional scaling loss function sstress. We conjecture that minimum sstress solution will be biased towards regular positioning of clumps of points over the surface of a sphere.

A problem with standard printer scatterplot routines is that points are not adequately labeled. Four methods of generating printer plots are presented. All four methods allow multi-character point labels, and three of the methods can guarantee that no portion of the labels are hidden. This is accomplished by using varying amounts of metric and nonmetric distance information to locate the points.

A computer program can be a means of communicating the structure of an algorithm as well as a tool for data analysis. From this perspective high-level matrix-oriented languages like PROC MATRIX in the SAS system are especially useful because of their readability and compactness. An algorithm for the joint analysis of dissimilarity and preference data using maximum likelihood estimation is presented in PROC MATRIX code.