Multicomponent latent trait models for ability tests

A major research direction for ability measurement has been to identify the information-processes that are involved in solving test items through mathematical modeling of item difficulty. However, this research has had limited impact on ability measurement, since person parameters are not included in the process models. The current paper presents some multicomponent latent trait models for reproducing test performance from both item and person parameters on processing components. Components are identified from item subtasks, in which performance is a logistic function (i.e., Rasch model) of person and item parameters, and then are combined according to a mathematical model of processing on the composite item.The author would like to thank David Thissen for his invaluable insights concerning this model and an anonymous reviewer for his suggestion about the sample space for the model.This research was partially supported by National Institute of Education grant number NIE-6-7-0156 to Susan E. Whitely, principal investigator. However the opinions expressed herein do not necessarily reflect the position or policy of the National Institute of Education, and no official endorsement by the National Institute of Education should be referred. Part of this paper was presented at the annual meeting of thePsychometric Society, Monterey, California: June, 1979.     

Reviews

Chris M. Anson, Lesley K. Cafarelli, Carol Rutz and Michelle R. Weis (eds) Dilemmas in Teaching: Cases for Collaborative Faculty Reflection Patricia Senn Breivik Student Learning in the Information Age Barbara E. Walvoord and Virginai Johnson Anderson Effective Grading: A Tool for Learning and Assessment William E. Campbell and Karl A. Smith (eds) New Paradigms for College Teaching Ann Intili Morey and Margie K. Kitano Multicultural Course Transformation in Higher Education Francis X. S. J. Clooney Hindu Wisdom for All God's Children Stephen R. Haynes Holocaust Education and the Church-Related College: Restoring Ruptured Traditions Warren A. Nord Religion and American Education: Rethinking a National Dilemma D. G. Hart and R. Albert Mohler, Jr (eds) Theological Education in the Evangelical Tradition Patrick W. Carey and Earl C. S. J. Muller (eds) Theological Education in the Catholic Tradition: Contemporary Challenges     

How can the federal government help education-related clearinghouses?

A survey of 100 education-related clearinghouses reveals that most are supported by the federal government; there is a great deal of redundancy among them in content and types of information covered; and that with the exception of the ERIC system clearinghouses, there is little coordination among them. This article suggests how Congress and the Department of Education can influence and coordinate clearinghouse activities to make it easier for educators to acquire the information they need to cope with the knowledge explosion expected to continue into the 1990s. Susan S. Klein is a senior staff member in the Office of Educational Research and Improvement, U.S. Department of Education, where she has worked with the ERIC Clearinghouses. Dr. Klein is now providing technical assistance on dissemination issues to the Select Education Subcommittee of the House of Representatives. Over the years she has helped manage research, evaluation, and dissemination programs in the National Institute of Education and the U.S. Office of Education. She has published in the areas of educational equity, dissemination, and evaluation, and recently edited and contributed to a special issue ofKnowledge, Creation, Diffusion, Utilization on “Federal Programs in Educational Dissemination.” She is on the board of the Knowledge Utilization Society.     

A lower bound to the probability of choosing the optimal passing score for a mastery test when there is an external criterion

Recently there has been interest in the problem of determining an optimal passing score for a mastery test when the purpose of the test is to predict success or failure on an external criterion. For the case of constant losses for the two error types, a method of determining an optimal passing score is readily derived using standard techniques. The purpose of this note is to describe a lower bound to the probability of identifying an optimal passing score based on a random sample ofN examinees.The work upon which this publication is based was performed pursuant to a grant [contract] with the National Institute of Education, Department of Health, Education and Welfare. Points of view or opinions stated do not necessarily represent official NIE position or policy.     

Racial and ethnic differences in motivation for educational achievement in the United States

Data from the National Educational Longitudinal Study [National Educational Longitudinal Study, (1994). National Educational Longitudinal Study: second follow-up (Report No.94-374). Washington, DC: U.S. Department of Education] show that on standardised scores in mathematics, reading and science, the highest mean scores are obtained by Asians and whites and lower scores are obtained by Hispanics and blacks. The same differences are present for the number of hours per week devoted to homework. It is suggested that motivational differences expressed in the amount of homework undertaken contribute to the group differences in educational achievement. Statistically significant correlations between the amount of homework and educational achievement support this hypothesis. There are also group differences in intelligence parallel to those in educational achievement, suggesting both intelligence and motivation are involved in racial and ethnic differences in educational achievement.     

Perceived influences on career choices of eleventh graders: Sex,SES, and ethnic group comparisons

The project Sex-Role Values and Career Decision Making was conducted to examine the responses of eleventh-grade high school students to sex-role-related values and to relate these responses to their educational and occupational aspirations. The concern of the present article is the influence of Sex, SES (socioeconomic status), and ethnicity on the reasons students give for their career choices. While students' responses were found to be generally similar across Sex, SES, and ethnic groups, the results indicated that females were significantly less likely than males to mention practical considerations, money, prestige, or status as elements in their career decisions, and more likely to mention helping others and personal achievement. The implications of these sex differences for sex equality in the career selection process are considered.The project reported on in this article was performed pursuant to a grant from the National Institute of Education, Department of Health, Education and Welfare. The opinions expressed here do not necessarily reflect the position or policy of the National Institute of Education, and no official endorsement by the National Institute of Education should be inferred.     

“Sherry’s Secret”

The case and commentaries below were developed as part of a project, Graduate Research Ethics Education, undertaken by the Association for Practical and Professional Ethics with funding from the National Science Foundation (NSF Grant No. SBR 9421897 and NSF Grant No. 9817880). The project aims at training graduate students in research ethics and building a community of scientists and engineers who are interested in and capable of teaching research ethics. As part of the project, each graduate student participant develops a case for use in teaching and writes a commentary to go with the case, and then a staff member is asked to write additional commentary on the case. The case below was written in the second year of the project and was published in Research Ethics: Cases and Commentaries edited by B. Schrag, Association for Practical and Professional Ethics, Bloomington, Indiana, Vol. II (1998). Publication of these cases and commentaries will be a recurring feature of Science and Engineering Ethics.     

On two-sided orthogonal procrustes problems

A least squares method for approximating a given symmetric matrixB by another matrixB which is orthogonally similar to a second given matrixA is derived and then generalized to nonsymmetric (but square)A andB. A possible application to ordering problems is discussed.This work was partially supported as project No. 083 by the Ohio State University, College of Education Research Grants and Leaves Program and subsequently as project I RO3 MH14097-01 by the National Institute of Mental Health. Free computer time was provided by the Ohio State University Computer Center. The writer is also pleased to record his appreciation for the time and assistance awarded to him most generously by Professors D. R. Whitney and J. S. Rustagi of the Ohio State University Mathematics Department.     

Information dissemination in early childhood education

Trends and issues in the dissemination of knowledge are discussed in terms of current trends. The general trends include the rapid rate at which new journals and documents are produced and increasing specialization in the field. Among the issues discussed are the optimum information hypothesis, optimum conceptual size of information, vividness and propitiousness of the information, and orientations to knowledge of subcultures within a professional field. The field of early childhood education is used as the example of each trend and issue. Lilian G. Katz is Professor of Early Childhood Education at the University of Illinois (Urbana-Champaign) where she is also Director of the ERIC Clearinghouse on Elementary and Early Childhood Education. She is currently President of the National Association for the Education of Young Children. Professor Katz is author of more than one hundred articles, chapters, and books about early childhood, teacher education, and parenting. Her most recent book isEngaging Children’s Minds: The Project Approach (with Sylvia Chard).     

A general latent trait model for response processes

The purpose of the current paper is to propose a general multicomponent latent trait model (GLTM) for response processes. The proposed model combines the linear logistic latent trait (LLTM) with the multicomponent latent trait model (MLTM). As with both LLTM and MLTM, the general multicomponent latent trait model can be used to (1) test hypotheses about the theoretical variables that underlie response difficulty and (2) estimate parameters that describe test items by basic substantive properties. However, GLTM contains both component outcomes and complexity factors in a single model and may be applied to data that neither LLTM nor MLTM can handle. Joint maximum likelihood estimators are presented for the parameters of GLTM and an application to cognitive test items is described.This research was partially supported by the National Institute of Education grant number NIE-6-7-0156 to Susan Embretson (Whitely), principal investigator. However the optinions expressed herein do not necessarily reflect the position or policy of the National Institute of Education, and no official endorsement by the National Institute of Education should be inferred.     

The Relationship Between General Population Suicide Rates and Educational Attainment: A Cross‐National Study

Suicides are associated with both high and low levels of intelligence and educational attainment in both individual‐level and aggregate‐level studies. A cross‐national study examining the relationship between general population suicide rates (y) and educational attainment (x) was undertaken with the a priori hypothesis that the relationship would be curvilinear and follow a U‐shaped curve with the quadratic equation Y = A + BX + CX², where A, B, and C are constants. Data on suicide rates and the Education Index (a proxy measure of educational attainment) were ascertained from the World Health Organization and the United Nations Web sites, respectively. The main finding was the predicted curvilinear relationship between general population suicide rates, in both sexes, and the Education Index fit the above quadratic equation. Given the cross‐sectional study design, a causal relationship cannot be assumed. The impact of educational attainment on general population suicide rates may occur through interaction with other factors, mediation of the effects of other factors, or by its effects being mediated by other factors, and require further study.     

Classroom behavior and children with mental retardation: Comparison of children with and without ADHD

Thirty-four children (ages 6–12 years) with moderate to borderline mental retardation were studied in a laboratory classroom setting to determine whether children identified as having attention deficit hyperactivity disorder on the basis of Conners Questionnaires differed in classroom behavior. Half of the children scored 15 or greater on both the Parent and Teacher Conners; the remaining children scored 11 or less. All were participants in a Saturday Education Program serving children with mental retardation. Direct observation of the laboratory classroom documented significant differences between groups on measures of on-task behavior and fidgetiness, especially during situations where little direct teacher feedback or supervision was available. Saturday Education Program staff, while blind as to group designation, rated the two groups as differing significantly on all scales of two standardized behavior problem checklists. Checklists by parents and teachers appear to be valid measures of classroom behavior of children with moderate to borderline mental retardation.This research was supported by a grant to the first author from the National Institutes of Child Health and Human Development, U.S. Department of Health and Human Services, grant No. 1R29HD26186-01A1. The authors gratefully acknowledge the assistance of the staff of Children's Hospital of Pittsburgh's Saturday Education Program: Nancy Hall, Aimee Hart, Phyllis Loeffler, Robin Nelson, Christina Poljak, Kelley Sacco, Sarah Stewart, and Mary Zuberbuehler.     

Cognitive engagement variations among students of different ability level and sex in a computer problem solving game

The study investigated the cognitive engagement processes used by more and less successful learners in a computer problem solving game. These engagement variations were also related to sex and ability differences among students. Performance and engagement were monitored interactively as students learned a computer problem solving game; student comments and notes were also recorded. Results showed the records of more and less successful students to be distinguished by the spontaneous use of self-regulated learning processes — a sophisticated form of cognitive engagement. More successful students also appeared to shift cognitive engagement levels in response to computer game feedback. Success on the computer task and cognitive engagement variations were correlated with student differences in both ability and sex in this sample.This study was funded by the National Institute of Education, Grant No. 400-83-0017. Opinions, findings, conclusions, and recommendations expressed in this study do not necessarily reflect the views of the National Institute of Education. The authors wish to thank Marcia Linn and Charles Fisher for their helpful advice, and Susanne Lajoie who served as second rater. Mary Rohrkemper and the Education and Child Development doctoral students at Bryn Mawr College also provided critical suggestions.     

“Think Aloud”: A program for developing self-control in young aggressive boys

Think Aloud was designed as a training program to improve self-control in 6- to 8-year-old boys. It involved modeling and verbalization of cognitive activity to foster use of verbal mediation skills in dealing with both cognitive and interpersonal problems. It was hypothesized that this training would lead to improvement in test performance and teacher ratings of classroom behavior in hyperaggressive boys. Twelve aggressive second grade boys participated in daily, 30-minute, individual sessions for 6 weeks. Normal and aggressive control subjects received no intervention. Teachers rated both trained and untrained aggressive boys as improving in aggressive behaviors but they rated the experimental group as showing improvement on a significantly larger number of prosocial behaviors. The pattern of performance on cognitive tests also changed significantly in the experimental group. On pretest, their pattern differed from normals and resembled the aggressive control group, while on posttest their pattern resembled normals and differed from aggressive controls. Suggestions were made concerning additional refinements needed in the program, but overall results indicated potential value in the present approach for providing assistance to aggressive boys in the early grades.This investigation, from the Departments of Pediatrics and Psychiatry, University of Colorado Medical School, was supported in part by a Research Scientist Award No. MK2-47 356 from the National Institute of Mental Health and by Grant No. NEG 003-0029 from the National Institute of Education. However, the opinions expressed herein do not necessarily reflect the position or policy of the NIE, and no official endorsement by the National Institute of Education should be inferred.We are grateful to Mary Ann Bash and Margaret Simmons for their assistance in carrying out the program and to the Denver Public Schools for their continued cooperation.     

Some properties of binormamin

Three properties of the binormamin criterion for analytic transformation in factor analysis are discussed. Particular reference is made to Carroll's oblimin class of criteria.The research reported in this note was supported in part by the Program in Applied Mathematics and Statistics. National Science Foundation, and by the National Institute of Education, Department of Health, Education, and Welfare.     

Continuous self-monitoring of discomfort in the dental chair and feedback to the dentist

The purpose of this study was to examine a continuous measurement of discomfort given by patients during aversive and nonaversive dental activities. To demonstrate the sensitivity of the measurement, the degree of feedback to the dentist about discomfort and the belief in that feedback were varied during oral examination, topical application, and injection of anesthesia. Patients operated buttons which were connected to a recorder and to light which signaled levels of discomfort to the dentist. The lights were operating during the dental activities for the Actual Feedback Group but not for the Belief in Feedback or the No Feedback Group. Subjective ratings of discomfort were also taken after each dental activity. The behaviorally based self-monitoring measure was more sensitive to variations in dental activities than were self-ratings. It showed differences across groups during the aversive, but not the nonaversive, events; showed differences in the delay of discomfort across groups; and suggested a decay in the belief in feedback effect with noncontingent dental response to discomfort responses.This study was supported in part by Research and Training Center Grant 16-P-56812, RT-13 from the National Institute of Handicapped Research, Office of Special Education, Department of Education.     

Estimating true score in the compound binomial error model

Several procedures have been proposed in the statistical literature for estimating simultaneously the mean of each ofk binomial populations. In terms of mental test theory, however, it is not clear that these procedures should be used when an item sampling model applies since the binomial error model is usually viewed as an oversimplification of the true situation. In this study we compare empirically several of these estimation techniques. Particular attention is given to situations where observations are generated according to a two-term approximation to the compound binomial distribution.The author would like to thank Shelley Niwa for writing the computer programs used in this study.The work upon which this publication is based was performed pursuant to Grant # NIE-G-76-0083 with the National Institute of Education, Department of Health, Education and Welfare. Points of view or opinions stated do not necessarily represent official NIE position or policy.     

Sleep deprivation in Air National Guard medical personnel responding to simulated disaster-training exercises

National Guard personnel remain largely unstudied within the sleep research community, despite their unique and important role. In response, the purpose of this study was to investigate the extent of sleep deprivation in National Guard medical personnel from two separate Air Force Bases (AFBs) responding to simulated disaster-training exercises. National Guard medical personnel (N = 77) were fitted with wrist activity monitors (actigraphy) to objectively measure their sleep for 4 days of their civilian time (baseline), followed by a 4-day transition period from civilian to military duty, and a 3–5-day disaster-training exercise. Differences in sleep quantity, quality, and “cognitive effectiveness” were analyzed using generalized linear mixed models. Participants’ sleep quantity was significantly reduced from civilian to disaster-training periods, and their cognitive effectiveness also dropped significantly. National Guard medical personnel were sleep-deprived during a simulated disaster-training exercise, which, although a valid proxy for real-world disasters, is likely to be a conservative approximation of the stress and fatigue National Guard personnel experience during crisis response. As such, the need for targeted fatigue-related interventions to safeguard our service members during these critical times is clear.     

The use of children's drawings in multiple family group therapy

This paper describes the advantages, difficulties and techniques of including young children in multiple family group therapy (MFGT). Multiple family group therapy consists of weekly sessions where three or more families meet conjointly with a therapist or cotherapists. Clinical vignettes demonstrate how to use children's drawings with parents to improve family communication. The efficiency of MFGT is compared to family therapy or individual therapy. The effective use of this modality with some children under 10 years is discussed.This research was supported in part by Alcohol, Drug Abuse, and Mental Health Administration Psychiatry Education Branch Grant MH 13882 from the National Institute of Mental Health.