Effect size indices for analyses of measurement equivalence: understanding the practical importance of differences between groups

Because of the practical, theoretical, and legal implications of differential item functioning (DIF) for organizational assessments, studies of measurement equivalence are a necessary first step before scores can be compared across individuals from different groups. However, commonly recommended criteria for evaluating results from these analyses have several important limitations. The present study proposes an effect size index for confirmatory factor analytic (CFA) studies of measurement equivalence to address 1 of these limitations. The application of this index is illustrated with personality data from American English, Greek, and Chinese samples. Results showed a range of nonequivalence across these samples, and these differences were linked to the observed effects of DIF on the outcomes of the assessment (i.e., group-level mean differences and adverse impact).     

Proctored Versus Unproctored Internet Tests: Are unproctored noncognitive tests as predictive of job performance?

As the usage of unproctored Internet testing (UIT) increases in selection settings, concerns about the validity of such practices must be addressed. While recent examinations of the issue have focused primarily on the practicality, ethics, and potential legal ramifications of UIT, this paper provides an examination of the criterion‐related validity of unproctored assessments. Using a database of validity evidence, we examine the predictive validity of several noncognitive assessments (i.e., personality and biodata) with respect to a number of subjective and objective job performance metrics. Results generally indicate that assessments administered in proctored and unproctored settings have similar validities. Limitations of this research and implications for practice are discussed.     

Answering the Ethical Question

Many philosophers have attempted to answer the ‘ethical question’: can the ethical value of an artwork ever contribute to its aesthetic value, and if so, how? In this paper, I consider a methodological question that arises out of this discussion: should attempts to address the ethical question use analytic tools found in contemporary philosophical literature, art criticism, or some combination of the two? I concur with arguments proposed elsewhere, which suggest that art criticism has an important role to play in addressing the ethical question. However, I argue that any fruitful attempt to answer the question must defend some particular way of understanding the ethical value of artworks, which suggests that we should address what I label the ‘art question’: what is the role and importance of art? This question, I suggest, is one with which philosophers can usefully engage. This division of labour offers a way forward in addressing this important issue.     

The Unity of Language

This paper identifies the founding project of traditional philosophy of language as an attempt to unify the diversity and individuality of spoken language in order to produce a transpersonal intelligibility. The supposed necessary truth that we cannot directly understand what others say which underlies such a project is exposed as a willful avoidance of the discourse of others typical of masculine styles of communication.     

Personal moral philosophies and moral choice

The moral choices and post-transgression reactions of individuals who adopted varying personal moral philosophies were examined in an experimental setting that permitted the manipulation of the salience of moral norms and the nature of the consequences of one's actions. As predicted, the two situational variables had a strong impact on moral action; only 50.0% of the subjects chose to violate a moral norm when that norm was salient and they would personally benefit by their actions; this percentage increased to 76.2% in the other conditions. Personal ethical philosophies also influenced moral choices and post-transgression reactions, for more of the idealistic subjects chose to act immorally relative to the low idealists (91.66% vs 70.83%), and subjects who were low in both idealism and relativism were less likely to transgress a moral norm if they personally would benefit. The results lend support to the proposed interpersonal model of morality, particularly as applied to post-transgression reactions.     

Homework and achievement: Explaining the different strengths of relation at the elementary and secondary school levels

Four explanations were tested for why the correlation between homework and achievement is weaker in elementary school than secondary school. Eighty-two teachers answered questions about their homework practices, and their responses were related to their students' achievement test scores. No evidence was found to suggest the weaker correlation in elementary school associated with a restricted variation in amounts of homework in early grades nor that teachers assigned more homework to poor-performing classes. Evidence did suggest that teachers in early grades assigned homework more often to develop young students' management of time, a skill rarely measured on standardized achievement tests. Also consistent with this hypothesis, elementary school teachers were more likely to use homework to review class material and to go over homework in class, while secondary school teachers more often used homework to prepare for and enrich class lessons. Finally, there was weak evidence that young students who were struggling in school took more time to complete homework assignments.     

Confirmatory Validation and Measurement Equivalence of the Eating Loss of Control Scale in Binge Eating and Non-Clinical Samples

Although Loss of Control (LOC) is a transdiagnostic factor in eating pathology, there are few standalone assessments of LOC. The objective of this study was to evaluate the uni-dimensionality and measurement equivalence of the Eating Loss of Control Scale (ELOCS). Confirmatory factor analyses were used to achieve a well-fitting uni-dimensional model in clinical (N?=?226) and non-clinical (N?=?476) samples. Measurement equivalence was tested in a factor analytic framework, and effect sizes were computed to evaluate the impact of non-equivalence. A well-fitting model was achieved in both samples after the removal of 4 items. The instrument showed configural equivalence but not metric equivalence. Results suggest that the ELOCS is a reliable and valid measure of LOC in clinical and non-clinical samples. However, while the nature of the LOC construct is similar across binge eating and non-clinical participants, comparisons of ELOCS across these groups are affected by measurement non-equivalence. This research also revealed novel insights into the relative sensitivity of model fitting and effect size approaches to investigating measurement equivalence.