Direction of measurement: A source of misinterpretation.

Interpretation of psychological measures is sometimes based on relationships between test characteristics (factor loadings, proportion of items keyed True, etc.). The direction of measurement adopted for a scale often determines how test characteristics are recorded. Failure to regulate direction of measurement, called here direction error, produces misleading results by affecting the distribution and intercorrelations of test characteristics. Examples are drawn from criterion analysis, the study of acquiescence, social desirability, and communality. A method for regulating direction of measurement is discussed. Its rationale is based on a distinction between directional and differential measurement. (34 ref.) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Corrected estimates of WAIS—R short form reliability and standard error of measurement.

Corrects computation and rounding errors in composite reliability estimates for the summary measures of the complete Wechsler Adult Intelligence Scale--Revised (WAIS--R) and the 7-subtest short form (D. Schretlen, R. H. B. Benedict, and J. H. Bobholz; see record 1995-04011-001) to provide more accurate reliability and standard error of measurement information. Composite reliabilities for the summary scores with both WAIS-R forms and standard errors of measurement for the 7-subtest short form and the complete WAIS-R summary scores are presented. Standard deviations for the IQ scores are also summarized. These values differ from the sum of scaled scores that appear in the WAIS-R manual (D. Wechsler, 1981). (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Estimating the standard error of projected dollar gains in utility analysis.

Although attention given to the utility analysis of personnel interventions has substantially increased recently, researchers have not addressed the problem of the standard error of utility estimates. The method for estimating such standard errors is presented and demonstrated in this article. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The standard problem: Meaning and values in measurement and evaluation.

Discusses the concepts of construct and content validity, the requirements of convergent and discriminant evidence, norm and criterion-referenced interpretations, values in measurement and the uses of counterhypotheses, and the identification of bias. The importance of construct-referencing all measurement is noted. The need for a dialectical evaluation where a particular thesis is confronted with its antithetical elements is stressed. This approach should help uncover assumptions and ideologies implicit in many measurement and evaluation activities. (61 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The misinterpretation of the Westinghouse study: A reply to Zigler and Berman.

Replies to the criticism of E. Zigler and W. Berman (see record 1984-07983-001) in their examination of the recent history of early childhood intervention of the Westinghouse study conducted under the direction of the present author (1969). It is asserted that the Westinghouse study did not conclude that Head Start was a success or a failure. Findings of the study resulted in recommendations for expanding and enriching the program and a fuller test of the concept of intervention. (4 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Case histories in the great power of steady misinterpretation.

The widespread misrepresentation of behaviorism in the scientific and popular literature has caused its contributions to the understanding of behavior to be systematically ignored or denied. This misrepresentation is manifested, in large part, as a form of academic folklore that codifies erroneous accounts of behaviorism's assumptions, findings, and goals. This article examines 3 representative "case histories" of the academic folklore about behaviorism: its alleged environmentalism, totalitarian aims, and intellectual intolerance. Because academic folklore has been highly resistant to the corrective efforts of behaviorists, explicit strategies are suggested for identifying and correcting folklore and for promoting more effective interdisciplinary communication. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Concerns about misinterpretation and placement of blame.

Clarifies remarks made by E. Schopler (see record 1987-32878-001) in response to a comment by T. Smith (1988) on specific vs nonspecific (placebo) effects on treatment outcomes. While the use of electric shock to encourage social behavior in autistic children (O. T. Lovaas et al, 1965) was a mistake based on erroneous beliefs, the lesson to be learned is that punishment (such as belittling colleagues' mistaken efforts) is not a constructive method for inducing change. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The continuing mischaracterization of radical behaviorism.

Contrary to R. W. Sperry's (see record 1989-00022-001) characterization, radical behaviorism (RB) is not reductive or atomistic. RB's central concept of the response class in antiatomistic, and its emphasis on the experimental analysis of behavior is not reductive. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Assessing the validity of the achievement motive in the presence of random measurement error.

The presence of random measurement error in indicators of theoretical constructs biases observed estimates of relations among those constructs. Correcting for this bias is particularly important when random measurement error is substantial or is substantially different for indicators of distinct constructs included in a theoretical model. Validity assessment in the case of thematic apperceptive measures of the achievement motive (TAT n Achievement) has been vulnerable to interpretive errors because these indicators of the achievement motive are typically much less reliable than indicators of other constructs to which the motive may be related, and no correction has been made for the bias introduced by such differential measurement error. A causal modeling approach to validity assessment for TAT n Achievement is presented that incorporates explicit true-score measurement models of theoretical constructs. Data from J. Veroff et al (1981) on 413 adult US males confirm the hypothesis that the achievement motive construct is positively related to work satisfaction. Evidence for the discriminant validity of story content as opposed to story length, an issue raised in the literature on the TAT, is also presented in this nomological network. (56 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Norm-of-reaction: Definition and misinterpretation of animal research.

The development of a phenotype is due to an interaction of the genotype with the environment. Two terms have been used to describe the outcome of this interaction, the norm-of-reaction and the reaction range. The first represents the theoretically limitless distribution of the phenotypes that may be expressed by a given genotype. The reaction range implies an upper and lower limit for phenotype expression possible from a given genotype. A critical distinction between the reaction range and the norm-of-reaction is that the norm-of-reaction is a statement of the conceivable interactions found but does not imply any predictability other than that within the conditions previously tested experimentally, that is, the tails of a normal distribution are infinitely variable, whereas the concept of reaction range implies a limitation inherent in the genotype, that is, a finite range. Empirical support for the reaction-range concept is questionable. Animal studies cited in support of the reaction range have been inappropriately and incorrectly interpreted. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Three standard errors of measurement and the Stanford-Binet Intelligence Scale, Fourth Edition.

The standard errors of measurement provided for the Stanford-Binet Intelligence Scale—Fourth Edition are (a) of limited utility and (b) set about an inappropriate score for use under most circumstances. Instructions are offered for calculating predicted true scores, and a table of standard errors of measurement is provided. In combination with the predicted true scores, the table can be used to set confidence intervals that will likely encompass an examinee's true score at the time of assessment and to calculate a confidence zone that will likely include an examinee's obtained score on retesting. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Anthropometry in health assessment: the importance of measurement error

Anthropometry is the hallmark technique of biological anthropology, and has become increasingly important in health assessments across this century. Although the need for accurate anthropometric measurement has been repeatedly stressed, the ways in which measurement error can influence the characteristics of anthropometric data is poorly appreciated. In this article, guidelines for acceptable measurement error are examined critically, and in light of repeat measurements data collected by the two authors on adults in Papua New Guinea.     

Concerns about misinterpretation and uncritical acceptance of exaggerated claims.

Responds to T. Smith's (1988) concern that the present author (see record 1987-32878-001) overemphasized placebo effects in discussing treatment effectiveness in programs for autistic children and criticizes Smith for comparing the present author's study with that of O. I. Lovaas (see record 1987-16420-001). (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Detection system for ocular refractive error measurement

An automatic and objective system for measuring ocular refractive errors (myopia, hyperopia and astigmatism) was developed. The system consists of projecting a light target (a ring), using a diode laser (lambda = 850 nm), at the fundus of the patient's eye. The light beams scattered from the retina are submitted to an optical system and are analysed with regard to their vergence by a CCD detector (matrix). This system uses the same basic principle for the projection of beams into the tested eye as some commercial refractors, but it is innovative regarding the ring-shaped measuring target for the projection system and the detection system where a matrix detector provides a wider range of measurement and a less complex system for the optical alignment. Also a dedicated electronic circuit was not necessary for treating the electronic signals from the detector (as the usual refractors do); instead a commercial frame grabber was used and software based on the heuristic search technique was developed. All the guiding equations that describe the system as well as the image processing procedure are presented in detail. Measurements in model eyes and in human eyes are in good agreement with retinoscopic measurements and they are also as precise as these kinds of measurements require (0.125D and 5 degrees).     

A cautionary note on measurement error corrections in structural equation models.

It is commonly thought that structural equation modeling corrects estimated relationships among latent variables for the biasing effects of measurement error. The purpose of this article is to review the manner in which structural equation models control for measurement error and to demonstrate the conditions in which structural equation models do and do not correct for unreliability. Generalizability theory is used to demonstrate that there are multiple sources of error in most measurement systems and that applications of structural equation modeling rarely account for more than a single source of error. As a result, the parameter estimates in a structural equation model may be severely biased by unassessed sources of measurement error. Recommendations for modeling multiple sources of error in structural equation models are provided. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The continuing use and misuse of SAT scores.

The Scholastic Aptitude Test (SAT), the most widely publicized test taken by Americans, strongly influences public opinion about the quality of American schools. Unfortunately, the SAT scores not only have no statistical validity for tracking trends in the achievement of American students but actually show a perverse relationship to the trends in achievement as tracked by statistically valid scores. Thus the scores are quite misleading indicators of the quality of schools. The College Entrance Examination Board, a nonprofit institution established to foster excellence in education, clearly understands the statistical limitations of the SAT scores yet actively seeks annual publicity around the release of national, state, and school district SAT scores. This article questions whether the decision by the College Board to continue publishing aggregate SAT scores is in the public interest. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The ubiquitous male standard.

Addresses the general assumption that women would be better off if their behavior more closely resembled those of men, even if the behavior in question is the utilization of mental health services. (3 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Estimating correlations from epidemiological data in the presence of measurement error

Analysis of a major multi-site epidemiologic study of heart disease has required estimation of the pairwise correlation of several measurements across subpopulations. Because the measurements from each subpopulation were subject to sampling variability, the Pearson product moment estimator of these correlations produces biased estimates. This paper proposes a model that takes into account within and between sub-population variation, provides algorithms for obtaining maximum likelihood estimates of these correlations and discusses several approaches for obtaining interval estimates.     

Regression toward the mean associated with measurement error and the identification of improvement and deterioration in psychotherapy.

Several factors can cause posttherapy scores to regress (relative to pretherapy scores) toward a group mean. This article focuses on regression effects that are due to measurement error, and on methods used to evaluate pre- to posttherapy score changes that attempt to take these regression effects into account. Statistical and practical problems associated with these methods are discussed. In particular, a statistical problem is identified in the most recent article that advocates use of these methods. Consequences of ignoring this problem and a way of correcting it are presented. Five practical problems encountered in using a correct classical true-score theory method of identifying reliable changes (based on derivations of H. Gulliksen [1950] and F. M. Lord and M. R. Novick [1968]) are then presented. Finally, objectives of these methods are distinguished from objectives of other strategies used to evaluate changes in psychotherapy. (PsycINFO Database Record (c) 2010 APA, all rights reserved)