A comparison of regression and standard score discrepancy methods for learning disabilities identification: Effects on racial representation

Learning-disabled (LD) children are often identified for services on the basis of a discrepancy between their IQ and achievement scores. Comparisons between regression and standard score difference methods for determining IQ-achievement discrepancies have not considered the comparative effects of these methods on the racial composition of LD classes. A comparison of these methods shows that the standard score difference method produces disproportionate racial representation, whereas the regression method produces proportionate racial representation in LD classes. In addition, the regression method demonstrates advantages in measurement of discrepancies, LD program planning, and conformity with constitutional guarantees of equal protection under the law.     

Novel methods for analyzing multifaceted personality scales: sense of coherence and depression as an example

Multifaceted personality scales assess multiple related facets or dimensions and, as such, they are typically made up of correlated subscales. In some cases, the degree of correlation among subscales can be so high as to render the use of standard procedures for evaluating a subscale's relative importance (e.g., beta weights or bivariate correlations) dubious. In such cases of high predictor multicollinearity, researchers are faced with few viable options and, in response, many turn to multiple regression when examining predictor-criterion associations (for example, interpreting semipartial correlations and incremental variance estimates). In an effort to broaden researchers' options and thereby allow for greater interpretive clarity, z tests for comparing dependent zero-order correlations and R. G. Malgady's (1987) methods for comparing two dependent semipartial correlations and for comparing dependent semipartial and zero-order correlations are proposed as additional techniques for analyzing predictor (or subscale) criterion associations in the context of predictor collinearity. Worked examples of both techniques are provided, using a dataset on sense of coherence and depression. Finally, relevant computer programs for implementing the aforementioned techniques are noted.     

Defining severe discrepancy in the diagnosis of learning disabilities: A comparison of methods

Given the significant increase in the number of students identified as learning-disabled (LD) and the growing concern about the overidentification of LD cases, attention has been focused on methods for determining a severe discrepancy between ability and achievement. Two such methods (a z-score discrepancy and a regression procedure) were compared by means of two different cutoff procedures on scores for 236 LD referrals. These results were then contrasted with a policy dictating that the lowest-achieving of those referred be considered as LD. Each student was evaluated with an individual intelligence scale and an achievement test. The results indicated that the regression procedure identified fewer students than did the z-score method. When the percentage of identified children is held constant, the methods were similar with respect to the types of errors made (false positives and false negatives). Data indicated that selecting the lowest-achieving students would have yielded about the same percentage of correct decisions, as defined by the multidisciplinary team, as did the two discrepancy methods. The policy implications of these findings are also considered.     

Methodological considerations in the evaluation of differential components of supplementary education programs

Details procedures to be followed in analyzing multiple program options and time allocation for significant effects. A multiple-option supplementary education program was evaluated by the application of multiple regression analysis as a general data analytic system. One analysis reports the relative merits of supplementary education components when more than one type of program was operated by the same school system and when the criteria for evaluation were end-of-year achievement tests. A second evaluation demonstrates that an analysis of program input variables such as aide time allocation did produce significant improvement in achievement when an analysis of the differential effect of the input variables was considered. An incidental outcome of this study was that significant improvement in reading and mathematics achievement for children in supplementary education programs was more likely to occur with second- and third-grade pupils than with thise at later grade levels.     

Relating latent class membership to external variables: An overview

In this article we provide an overview of existing approaches for relating latent class membership to external variables of interest. We extend on the work of Nylund-Gibson et al. (Structural Equation Modeling: A Multidisciplinary Journal, 2019, 26, 967), who summarize models with distal outcomes by providing an overview of most recommended modeling options for models with covariates and larger models with multiple latent variables as well. We exemplify the modeling approaches using data from the General Social Survey for a model with a distal outcome where underlying model assumptions are violated, and a model with multiple latent variables. We discuss software availability and provide example syntax for the real data examples in Latent GOLD.     

A comparison of methods for calculating a severe discrepancy

Given the substantial rise in the number of students identified as learning-disabled, increasing attention has centered on methods for determining a severe discrepancy between ability and achievement. Using scores from 86 learning disabilities referrals, we compared four such methods (a z-score discrepancy, an estimated true score discrepancy, an unadjusted regression procedure, and an adjusted regression procedure). Each student was evaluated with the WISC-R, PIAT, and K-ABC. A high degree of agreement was found between z-score and estimated true score difference approaches. Less agreement was found between the unadjusted regression procedure and the other methods. It was concluded that the four methods cannot be used interchangeably in the calculation of severe discrepancies. Of the four methods that were analyzed, the unadjusted regression procedure selected the smallest percentage of students.     

Parent-child discrepancies in report of psychopathology: the contributions of response bias and parenting stress

This study explored the associations between response-bias features, parenting stress, and parent-child discrepancies in self-report and parent ratings of psychopathology in a sample of 153 preadolescents from an inpatient psychiatric setting. Correlational and multiple regression analyses utilized combinations of dissimulation (FB) and defensiveness (DEF) validity scales from the Personality Inventory for Youth (PIY; Lachar & Gruber, 1995) and Personality Inventory for Children (PIC-2; Lachar & Gruber, 2001) and components from Abidin's (1995) Parenting Stress Index (PSI) to predict normalized parent-child discrepancies between the PIY/PIC-2 clinical scales. Response-bias features were significantly associated with hypothesized patterns of under- and overreporting and accounted for most of the variance in parent-child discrepancies. Although child stress components of the PSI demonstrated a generalized pattern of moderate relationships with parent-child discrepancies, parent stress components demonstrated a weaker and more specific pattern of relationships.     

Logistic regression

Logistic regression has probably been underutilized in clinical investigations of personality because of its relatively recent development (dictated by the need for computer programs to obtain maximum likelihood estimates), and the fact that use has been largely confined to the fields of biostatistics, epidemiology, and economics Its use should be given serious consideration when the outcome of interest is dichotomous (or polychotomous) in nature and the predictors of interest may be categorical or continuous. The logit transformation is quite tractable mathematically, and it embodies the notion of threshold, which may have relevance for many of the variables that are of interest to investigators in the field of personality. Furthermore, investigators with experience in multiple linear regression or contingency table analysis should have little trouble in transitioning to logistic regression. Logistic regression programs are readily available in the major statistical packages, all of which provide fairly standard output.     

Logistic Regression

Logistic regression has probably been underutilized in clinical investigations of personality because of its relatively recent development (dictated by the need for computer programs to obtain maximum likelihood estimates), and the fact that use has been largely confined to the fields of biostatistics, epidemiology, and economics Its use should be given serious consideration when the outcome of interest is dichotomous (or polychotomous) in nature and the predictors of interest may be categorical or continuous. The logit transformation is quite tractable mathematically, and it embodies the notion of threshold, which may have relevance for many of the variables that are of interest to investigators in the field of personality. Furthermore, investigators with experience in multiple linear regression or contingency table analysis should have little trouble in transitioning to logistic regression. Logistic regression programs are readily available in the major statistical packages, all of which provide fairly standard output.     

Identifying children with learning disabilities: When is a discrepancy severe?

Identification of children with learning disabilities is based on the notion of a significant discrepancy between ability and achievement. Current federal guidelines do not specify the extent of such discrepancies but indicate they should be “severe”. Local education agencies have adopted criteria suggested by professionals or formulated their own operational criteria for identification of learning disabled children. In this research, we examined the extent to which identification as learning disabled is a function of the criteria used to define “severe discrepancy”, and the extent to which different classifications would result from use of different criteria. A school district made identification decisions for 51 students referred because they were experiencing academic difficulties; they found 24 students LD. The school identification decisions, based on application of a severe discrepancy on the Woodcock-Johnson Psycho-Educational Battery, did not correlate with decisions based on application of the federal definition. Implications for decision-making practices are discussed.     

Developmental Patterns and Use of the Wisconsin Card Sorting Test for Children and Adolescents with Learning Disabilities

This study examined the Wisconsin Card Sorting Test (WCST) by testing 129 children and adolescents with learning disabilities (LD) who were between 7 and 13 years of age. Developmental trends were examined across age groups using scores from the WCST. Several scales yielded developmental patterns, supported by statistically significant main effects for age. Additionally, multiple regression analyses were run examining the relationship of the WCST with other measures. The models yielded were in predicted directions. The results of this study support the clinical utility of the WCST in children and adolescents with LD.     

SOCIAL INTERACTIONS IN THREE SUPPORTED EMPLOYMENT OPTIONS: A COMPARATIVE ANALYSIS

Controversy exists over the benefits that workers with severe disabilities accrue under different supported employment options. This study focused upon one benefit of supported employment: social integration. Direct observation procedures were used to assess the social interactions of 37 adults with severe disabilities in 18 employment programs representing three different supported employment contexts (individual, enclave, and work crew). Results indicated that workers employed in individual and enclave programs had significantly more contact with nondisabled persons than did members of work crews. No differences were detected in the social contact rate between disabled and nondisabled workers in individual versus enclave sites. Furthermore, few differences in type of interactions across the three different work options were revealed. Results suggest that both individual and enclave models are capable of facilitating social integration. However, characteristics of specific job sites, more so than the employment model per se, may determine whether a particular employment setting is conducive to social integration.     

An example of cooperating compact data analysis programs

Some user-oriented compact data analysis programs are described. One program is useful for transforming and reformatting data, and the others perform analysis of variance and multiple regression. Along with other programs not described here, these form an adequate statistical package without sacrificing ease of use or computational power.     

When choices give in to temptations: Explaining the disagreement among importance measures

Respondents’ overt statements of relative importance rarely correspond to weights derived from a regression analysis of their decisions. This paper conjectures that differential effects of high-level goals on importance beliefs and choices can explain these discrepancies. It is argued that the goal to justify decisions influences importance beliefs more than choices whereas the goal to assess preferences accurately affects choices more than importance beliefs. It is also argued that differential effects of high-level goals on importance statements and choices vary as a function of whether decision-maker controls the information flow and the extent of prior knowledge and experiences with choice options. These predictions were tested within the context of a contraceptive decision-making task. Choices among contraceptives made the justification goal salient to subjects by requiring tradeoffs between attributes that are either considered rational or tempting in making such decisions (e.g., health risks vs. pleasure/convenience). As predicted, subjects assigned larger importance weights to rational attributes in their subjective evaluations than in their choices whereas the impact of tempting attributes was stronger for choices than for subjective importance evaluations. Moreover, these observed discrepancies between importance measures were reduced in favor of rational attributes when subjects controlled the information flow and could not access their prior experiences. Overall, the results suggest that, although tempting attributes affect choices, decision makers appear to be unwilling to acknowledge the impact of tempting attributes on their decisions in judging attribute importance.     

AN ASSIMILATION THEORY PERSPECTIVE OF COMMUNICATION APPREHENSION

In this study, both the dynamic and stable qualities of communication apprehension are examined from an assimilation theory perspective. Based upon assimilation theory, PRC A scores obtained after an intervening speech performance are predicted from initial levels of communication apprehension and discrepancies between those initial levels and the levels of state anxiety experienced during speech performance. The results of multiple regression analysis indicate that both initial apprehension levels and the discrepancy variable contributed significantly to the prediction of post-intervention PRCA scores, a finding that supports an assimilation theory perspective of communication apprehension.     

Age, Gender, and Ethnicity Effects on Parent–Child Discrepancy Using Identical Item Measures

Objective assessment of child and adolescent behavioral and emotional symptoms is traditionally obtained from multiple sources. However, a substantial body of research indicates that parental and child reports provide significant amounts of contradicting diagnostic information. Although a large and growing body of research attempts to identify potential influences of discrepant reports, the current research improves upon previous research in three primary ways: using identical item measures, using expanded statistical analyses, and evaluating cultural influences on observed discrepancies. A total of 2,153 parent–child dyads completed ratings of child behavior and emotional functioning. Specifically, parents and children completed the Ohio Scales, an empirically supported, identical item measure. Generally, reporter agreement was greater than typically reported. Similar to previous research with clinical populations, parents reported greater levels of child problems than their children. While age was not associated with observed discrepancies, parents and daughters demonstrated greater discrepancies on fewer specific items while parents and sons demonstrated more pervasive yet less severe discrepancies. Additionally, Hispanic dyads demonstrated less discrepancy than did African American and Caucasian dyads independent of discrepancy analysis. Discrepancies must be measured using multiple statistical methods in order to understand patterns. Furthermore, discrepancy research must address key demographic factors (e.g., ethnicity, gender).     

Attention and executive function in children with and without single-suture craniosynostosis

Children with single-suture craniosynostosis (SSC) have higher rates of learning disabilities and related neurocognitive problems than unaffected peers. Executive function (EF) and attention are thought to be areas of particular vulnerability, though studies to date have been limited by small sample sizes and a lack of control groups. We evaluated 179 school-aged children with SSC (cases) and 183 unaffected controls at an average age of 7 years using clinician-administered and parent and teacher report measures of EF and attention. Among children with SSC, we examined differences as a function of suture location (sagittal, metopic, unicoronal, or lambdoid) and age of corrective surgery. We used linear regression analyses, adjusted for potential confounders, to compare the two groups on all outcome measures. Cases scored lower than controls on most measures, though the magnitude of these differences was small and most were statistically insignificant. The largest relative deficit was on a measure of inhibitory control. Results changed little in sensitivity analyses adjusting for potential attrition bias and for the effects of developmental and academic interventions. Among cases, there were few differences in relation to the location of suture fusion or timing of surgery. Overall, we found limited evidence of broad deficits in EF or attention in children with SSC relative to unaffected controls. Neurocognitive development for children with SSC appears to be variable, across affected children and outcomes assessed. Further research is needed to understand the potential sources of this variability.     

FIXED EFFECTS ANALYSIS OF VARIANCE BY REGRESSION ANALYSIS

This paper is concerned with the solution of typical analysis of variance problems using general purpose multiple regression computer programs. Specific models, restrictions on the parameters for hypothesis testing, and computational aspects are discussed. It is argued that this approach has many pedagogical advantages over traditional procedures.     

Testing Informant Discrepancies as Predictors of Early Adolescent Psychopathology: Why Difference Scores Cannot Tell You What You Want to Know and How Polynomial Regression May

Multiple informants commonly disagree when reporting child and family behavior. In many studies of informant discrepancies, researchers take the difference between two informants’ reports and seek to examine the link between this difference score and external constructs (e.g., child maladjustment). In this paper, we review two reasons why difference scores cannot serve as unambiguous predictors of outcomes. Further, we use polynomial regression analyses to both test the validity of difference scores and provide a more direct test of the hypothesis that discrepancies in parent and child reports predict child psychopathology. Data from 218 parent-adolescent dyads (M adolescent age?=?11.5 years, 51 % female; 49 % European American, 47 % African American) were used to predict adolescent-reported antisocial behavior and depression from parent and adolescent reports of parent-adolescent conflict, parental knowledge, parental acceptance, adolescent rule-breaking behavior, and adolescent pubertal development. Results demonstrate that analyses using difference scores do not provide valid tests of the utility of informant discrepancies in predicting adolescent psychosocial maladjustment. However, interaction terms in polynomial regression analyses provide evidence that informant discrepancies predict child psychopathology. Parent-adolescent informant discrepancies predict adolescent psychopathology but researchers should avoid using difference scores to measure informant discrepancies. Polynomial regression analyses provide more comprehensive and accurate tests of whether informant discrepancies predict child and adolescent psychopathology.     

Inclusive and exclusive modes of thinking: Studies of prediction, preference, and social perception during parliamentary elections

The 1999 Israeli multi-party parliamentary election was used for studying the effects of inclusive and exclusive modes of thinking. In three experiments, we tested a theoretical framework whose major elements are the justification process, a distinction between middling and clearcut options, and the use of inclusion and exclusion threshold criteria. In Studies 1-2, respondents were asked to predict either of which parties would win seats in the parliament (inclusion) or which parties would fail to win seats in the parliament (exclusion). In Study 2, respondents were also asked to use inclusive or exclusive modes to indicate their preferences and in Study 3, they were asked to make either inclusive or exclusive judgments about the platforms of two extreme political parties. We found consistent discrepancies between the outcomes of inclusion and exclusion processes, such that choice sets generated in exclusion were larger than those generated in inclusion. A second major finding was the option effect, namely, the discrepancies between the two modes of thinking were larger for middling than for clearcut options. The third main finding was an expertise effect: the less knowledgeable respondents exhibited greater discrepancies than did the more knowledgeable ones. Our theoretical framework accounts for the inclusion-exclusion discrepancy, the option effect, and the expertise effect. We discuss the implications of these findings for judgment and choice in social settings and also for the understanding of question-form effects in opinion surveys—in particular, the allow-forbid effect.