Factor structure in groups selected on observed scores

A new method is proposed for estimating factor means and factor covariances in a group of individuals selected on their observed scores. The selection variable is, for example, the total score on an admissions test. Given a factor model for the test items based on the group of test takers, we may be interested in the factor structure for those in the top quartile. The differences in factor means and covariances between this selected group and the full group gives useful information both on successful test performance and on test validity. The new method draws on the classic Pearson-Lawley selection formulas. It avoids the fallacy of factor analysis on the selected group, which would lead to incorrect estimates. The new method is applied to a simple factor structure model for the GMAT test. Although the majority of the GMAT items test verbal skills, it is found that a quantitative factor shows the greatest change in moving from average to top quartile test takers.     

STRATÉGIES COGNITIVES ET PROCESSUS D'AUTORÉGULATION CHEZ DES FAMILLES EN SITUATION DE RÉSOLUTION DE PROBLÈMES LOGIQUES*

The family is a fundamental learning environment for many basic skills such as the ability to solve everyday domestic problems. A lack of competence in this type of problem solving would expose the individual to more frustration and possibly create the conditions for greater aggression. Forty-two low SES families, each including an aggressive boy, were invited to the laboratory for a problem-solving session on two occasions, at an interval of two years. Subjects were asked to find four preset combinations of colours by systematic permutations of four colours using a computer. Three types of cognitive performance were examined: resolution strategies, autoregulation strategies and the success rate in finding the solution. Results showed that most of the families were consistent in their use of a non-systematic strategy. Although some improvement in planning is observed during the second testing, no other improvement in autoregulation strategies was observed. In general, families had a better rate of success in finding the solution in the second session. The low cognitive level of these families and its stability are discussed. Étant donné que la famille constitue un terrain privilégié d'apprentissage, l'aggressivité comportementale de certains enfants pourrait résider dans le peu d'opportunités offertes par leur famille d'apprendre à affronter les problèmes de la vie quotidienne d'une manière réfléchie. Quarante-deux familles de milieu socio-économique faible, dont un des enfants est à risque d'inadaptation sociale et dont les parents sont peu scolarisés, ont à résoudre un problème nécessitant l'intelligence logique et ce, à deux ans d'intervalle (T-1 et T-2). La tâche consite à résoudre un problème de permutations à quatre éléments et se présente sous la forme d'un jeu d'ordinateur. Le fonctionnement cognitif est examiné selon trois dimensions: les stratégies cognitivcs de résolution, les stratégies d'autorégulation exercées, sur la démarche cognitive et l'issue de la démarche cognitive. L'examen des stratégies cognitives révèle que la majorité des familles utilisent une approche non stratégique et que cette approche est maintenue aussi bien à l'intérieur d'une séance donnée que d'une séance à l'autre. Exception faite de l'amélioration relevée à la séance 2 quant au contrôle exercé par les familles sur le déroulement de leur démarche cognitive, aucun changement n'émerge sur les autres critères de l'autorégulation. Finalement, les familles obtiennent une meilleure performance à la deuxième séance. La discussion porte sur la relative stabilité du niveau de fonctionnement cognitif des familles ainsi que sur la pauvreté apparente de leur répertoire de schèmes.     

On structural equation modeling with data that are not missing completely at random

A general latent variable model is given which includes the specification of a missing data mechanism. This framework allows for an elucidating discussion of existing general multivariate theory bearing on maximum likelihood estimation with missing data. Here, missing completely at random is not a prerequisite for unbiased estimation in large samples, as when using the traditional listwise or pairwise present data approaches. The theory is connected with old and new results in the area of selection and factorial invariance. It is pointed out that in many applications, maximum likelihood estimation with missing data may be carried out by existing structural equation modeling software, such as LISREL and LISCOMP. Several sets of artifical data are generated within the general model framework. The proposed estimator is compared to the two traditional ones and found superior.The research of the first author was supported by grant No. SES-8312583 from the National Science Foundation and by a Spencer Foundation grant. We wish to thank Chuen-Rong Chan for drawing the path diagram.     

Three-dimensional perspective drawing of two-dimensional functions with microcomputers

In this paper, we present a BASIC program for Apple II series computers that allows the user to obtain perspective drawings of two-dimensional functions of known analytical expression. Also, we outline a procedure for obtaining perspective representations of two-dimensional arrays of data using the same program. The program should run on any computer with graphics mode with only slight modifications in the graphics commands.     

Factors related to eating disorders in young adolescent girls

The objective of this study was to identify factors related to eating disorders in young adolescent girls. Three hundred eighty-five girls who were attending a career conference at a midwestern university completed the Eating Disorder Instrument (EDI) along with a biographical data sheet. The EDI is designed for the assessment of psychological and behavior traits common in eating disorders. While 81% of the young subjects were assessed to be within the range for ideal weight or were underweight, 78% preferred to weigh less. Only 14% were satisfied with their current weight. Findings for each of the subscales used revealed significant differences among the girls based on intact versus broken family; subjects' actual and preferred weight; whether the family ate meals together; average grades; age and grade in school; fathers' occupation; future career plans; place of residence; and feelings toward their mothers.     

Beliefs about and experiences with battering: Women and men in two populations

A questionnaire was developed to measure beliefs about and experiences with violence in the family. Two groups of persons in two different states who had attended conferences on battered women participated in this research. Of the 177 subjects (84% women, 16% men), none of the men had been battered, yet over one-third of the women had been; more older women reported having been adult battering victims than did younger women; the women had less formal education than the men; the women in the lower educational groups were more likely to have been battered and to report fear of becoming victims; and the social service workers reported little fear of battering.     

A general structural equation model with dichotomous,ordered categorical,and continuous latent variable indicators

A structural equation model is proposed with a generalized measurement part, allowing for dichotomous and ordered categorical variables (indicators) in addition to continuous ones. A computationally feasible three-stage estimator is proposed for any combination of observed variable types. This approach provides large-sample chi-square tests of fit and standard errors of estimates for situations not previously covered. Two multiple-indicator modeling examples are given. One is a simultaneous analysis of two groups with a structural equation model underlying skewed Likert variables. The second is a longitudinal model with a structural model for multivariate probit regressions.This research was supported by Grant No. 81-IJ-CX-0015 from the National Institute of Justice, by Grant No. DA 01070 from the U.S. Public Health Service, and by Grant No. SES-8312583 from the National Science Foundation. I thank Julie Honig for drawing the figures. Requests for reprints should be sent to Bengt Muthén, Graduate School of Education, University of California, Los Angeles, California 90024.