Effect of Unequal Variances in Proficiency Distributions on Type-I Error of the Mantel-Haenszel Chi-square Test for Differential Item Functioning

Empirical studies demonstrated Type-I error (TIE) inflation (especially for highly discriminating easy items) of the Mantel-Haenszel chi-square test for differential item functioning (DIF), when data conformed to item response theory (IRT) models more complex than Rasch, and when IRT proficiency distributions differed only in means. However, no published study manipulated proficiency variance ratio (VR). Data were generated with the three-parameter logistic (3PL) IRT model. Proficiency VRs were 1, 2, 3, and 4. The present study suggests inflation may be greater, and may affect all highly discriminating items (low, moderate, and high difficulty), when IRT proficiency distributions of reference and focal groups differ also in variances. Inflation was greatest on the 21-item test (vs. 41) and 2,000 total sample size (vs. 1,000). Previous studies had not systematically examined sample size ratio. Sample size ratio of 1:1 produced greater TIE inflation than 3:1, but primarily for total sample size of 2,000.     

Sibling Differences in Divorced Families

Sibling differences in family processes and individual adjustment were examined for 133 sibling pairs (10–18 years old) in divorced families. Although all siblings differed, siblings who lived apart after their parents' divorce differed more than siblings who lived together, contradicting past research that found negligible effects of shared environment on sibling similarities. The possibility that siblings might live apart because they were initially more different was considered. This hypothesis was not supported in the limited tests permitted by the data. Differences in family processes were associated with differences in adjustment for pairs who lived together as well as pairs who lived apart.     

Technology policy as a stealth agent of global change

Drawing upon a year of ethnographic research with the Los Angeles public school system, this article follows the translation and negotiation of several key technology grants and their policies. It argues that as a global trend, myths of technological neutrality and transparency merely cloud the panoply of negotiations taking place in public organizations, subsequently removing those decisions from public participation or scrutiny. Technology policy thereby becomes a stealth agent of global change, which, ironically in this case, reinforces Fordist rigidities in technological realms that are typically viewed as supporting post‐Fordist flexibilities. Only by engaging with technology policy in all its complexity, the article concludes, can public institutions hope to achieve democratic participation and outcomes.     

Comparison of Factor Simplicity Indices for Dichotomous Data: DETECT R,Bentler's Simplicity Index,and the Loading Simplicity Index

A primary assumption underlying several of the common methods for modeling item response data is unidimensionality, that is, test items tap into only one latent trait. This assumption can be assessed several ways, using nonlinear factor analysis and DETECT, a method based on the item conditional covariances. When multidimensionality is identified, a question of interest concerns the degree to which individual items are related to the latent traits. In cases where an item response is primarily associated with one of these traits it is said that (approximate) simple structure exists, whereas when the item response is related to both traits, the structure is complex. This study investigated the performance of three indices designed to assess the underlying structure present in item response data, two of which are based on factor analysis and one on DETECT. Results of the Monte Carlo simulations show that none of the indices works uniformly well in identifying the structure underlying item responses, although the DETECT r-ratio might be promising in differentiating between approximate simple and complex structures under certain circumstances.     

African American Women’s Language Use in Response to Male Partners’ Condom Negotiation Tactics

African American women are vulnerable for sexual health risk; thus, condom use is essential. Guided by research linking goals to communicative content, this study explored women’s use of I-, you-, we-, and hedging language during condom negotiation. Female participants (N = 193) engaged in a condom negotiation role play with male confederates, where language use measures were coded. I-language was used the most frequently. Language use differed as a function of men’s tactics, such that women primarily used I-language in response to verbal attacks, you-language in response to seduction, and I- and we-language in response to information seeking. Women who engaged in more recent condom use were more likely to use you-language and, when confederates attacked, they responded with more you-language and less hedging.     

When Do Honors Programs Make the Grade? Conditional Effects on College Satisfaction,Achievement, Retention,and Graduation

Many people within and outside of higher education view honors programs as providing meaningful academic experiences that promote learning and growth for high-achieving students. To date, the research exploring the link between honors participation and college grades and retention has obtained mixed results; some of the seemingly conflicting findings may stem from the presence of methodological limitations, including the difficulty with adequately accounting for selection into honors programs. In addition, virtually no research has explored the conditions under which honors programs are most strongly related to desired outcomes. To provide a rigorous examination of the potential impact of this experience, this study conducted propensity score analyses with a large, multi-institutional, longitudinal sample of undergraduates at 4-year institutions. In the full sample, honors participation predicts greater college GPA and 4-year graduation, while it is unrelated to college satisfaction and retention. However, these results differ notably by institutional selectivity: Honors participation is associated with greater college GPA, retention to the third and fourth years of college, and 4-year graduation at less selective institutions, but it is significantly related only to GPA at more selective institutions. These relationships are also sometimes larger among students from historically underrepresented groups.     

Trajectories of Violent Behavior Among Females and Males

Both the psychological and criminological fields have long hypothesized the mechanisms that influence desistance from violent offending, but few studies have focused on violent females. This study identifies patterns of violent behavior across 7 years among 172 females and 172 matched males ages 15–24, testing if heterogeneity in violent offending is linked to (a) developmental change in impulse control and (b) attainment of adult milestones. Fewer females persist in violence (25%) than males (46%); 19% of males increase in violent behavior. Females who develop impulse control and are employed are more likely to desist from violence. Violent offending is unrelated to other adult milestones. Developmental increases in impulse control may trigger desistance, while employment may maintain desistance from violence.     

Revisiting the impact of part-time work on adolescent adjustment: distinguishing between selection and socialization using propensity score matching

The impact of part-time employment on adolescent functioning remains unclear because most studies fail to adequately control for differential selection into the workplace. The present study reanalyzes data from L. Steinberg, S. Fegley, and S. M. Dornbusch (1993) using multiple imputation, which minimizes bias in effect size estimation, and 2 types of propensity score matching, to account for selection effects. In this sample (N = 1,792; Grades 10-11, M = 16.26), youth who begin working more than 20 hr per week evince declines in school engagement and increases in substance use and delinquency compared with youth who remain unemployed. Conversely, working 20 hr or less a week has negligible effects, positive or negative, on academic, psychological, or behavioral outcomes.