An interval estimate for making statistical inferences about true scores

A numerical procedure is outlined for obtaining an interval estimate of the regression of true score on observed score. Only the frequency distribution of observed scores is needed for this. The procedure assumes that the conditional distribution of observed scores for fixed true score is binomial. The procedure is applied to several sets of test data.This research was sponsored in part by the Personnel and Training Research Programs, Psychological Sciences Division, Office of Naval Research, under Contract No. N00014-69-C-0017, Contract Authority Identification Number, NR No. 150-303, and Educational Testing Service. Reproduction in whole or in part is permitted for any purpose of the United States Government.     

A fresh look at the retention-promotion controversy

This article provides an overview of several issues relative to retention of school children. Included is a historical perspective on the present retention-promotion controversy, information on retention policies and retention prevalence rates, a review of research on the effectiveness of retention, and a discussion of several factors that should be considered by psychologists faced with the problem of making retention and promotion recommendations.     

A theoretical distribution for mental test scores

The negative hypergeometric distribution of raw scores on mental tests is derived from certain assumptions relating to test theory. This result is checked empirically in a number of examples. Further derivations lead to the bivariate distribution of parallel tests which is also verified with actual data. The bivariate distribution of raw score and true score is also derived from a further assumption. This distribution is used to set confidence limits for true scores for persons with a given raw score.This work was supported in part by contract Nonr-2752(00) between the Office of Naval Research and Educational Testing Service. Reproduction in whole or in part for any purpose of the United States Government is permitted.     

Cutting scores and errors of measurement

Arguments for using multiple cutting scores are theoretically inapplicable when the selection measures are fallible. The effect of errors of measurement in altering the shape of some optimum selection regions is here investigated mathematically, with numerical illustrations, for the case of two selection variables.This work was supported by contract Nonr-2752(00) between the Office of Naval Research and Educational Testing Service. Reproduction in whole or in part for any purpose of the United States Government is permitted.     

Strategic Construction of Fitch-style Proofs

Symlog is a system for learning symbolic logic by computer that allows students to interactively construct proofs in Fitch-style natural deduction. On request, Symlog can provide guidance and advice to help a student narrow the gap between goal theorem and premises. To effectively implement this capability, the program was equipped with a theorem prover that constructs proofs using the same methods and techniques the students are being taught. This paper discusses some of the aspects of the theorem prover's design, including its set of proof-construction strategies, its unification algorithm as well as some of the tradeoffs between efficiency and pedagogy.     

EFFECTS OF CHILD BEHAVIOR CHANGE ON TEACHER VERBAL BEHAVIOR AND RATING OF STUDENT BEHAVIOR1

The relationship between student behavior change and its effect on teacher behavior was investigated. A total of six boys and their two male teachers from two fourth-grade classrooms served as subjects. In two multiple-baseline experiments, students were exposed successively to baseline, placebo-therapy (a control for teacher expectation of student change), active-therapy (contingencies for student behavior improvement), and a return to placebo-therapy phases. As student behavior (the independent variable) improved, daily teacher ratings of children improved moderately, and the percentage of teacher vocalizations in response to appropriate (as compared with inappropriate) child behavior increased markedly. The latter shift in the distribution of teacher vocalizations was found to be largely attributable to the increased availability of appropriate behavior to which teachers could respond. This study raises questions about similar findings in an earlier experiment by Sherman and Cormier (Journal of Applied Behavior Analysis, 1974, 7 , 11–21). First, the main measure of teacher verbal behavior in both this and the earlier study was considered to be insufficient as a measure of teacher change. It did not control for the expected effects of changes in the base rate of student appropriate behavior. Second, student behavior improvement did not appear to reinforce teacher behavior. This was attributed to the noncontingency of student improvement on any class of teacher behaviors. The possible reinforcing value of student behavior improvement for teachers was not challenged. Implications of rating changes were also discussed.