Modern robust data analysis methods: measures of central tendency

Various statistical methods, developed after 1970, offer the opportunity to substantially improve upon the power and accuracy of the conventional t test and analysis of variance methods for a wide range of commonly occurring situations. The authors briefly review some of the more fundamental problems with conventional methods based on means; provide some indication of why recent advances, based on robust measures of location (or central tendency), have practical value; and describe why modern investigations dealing with nonnormality find practical problems when comparing means, in contrast to earlier studies. Some suggestions are made about how to proceed when using modern methods.     

It's about timing and change: pubertal transition effects on symptoms of major depression among African American youths

Effects of early physical maturation and accelerated pubertal changes on symptoms of major depression were examined in 639 African American children. Three rival hypotheses, early timing, off-time, and stressful change, were tested using 2 waves of data (mean ages = 11 and 13 years). The pubertal effect operates differently according to children's gender and age. For girls, early maturation was consistently associated with elevated levels of depressive symptoms. For boys, early maturers manifested elevated levels of depression only at age 11, but these symptoms subsided by age 13. Boys who experienced accelerated pubertal growth over time displayed elevated symptom levels. Results support the early timing hypothesis for girls and the stressful change hypothesis for boys. Time at assessment is critical when examining boys' pubertal transition.     

Comparing dependent robust correlations

Let r₁ and r₂ be two dependent estimates of Pearson's correlation. There is a substantial literature on testing H₀ : ρ₁ = ρ₂, the hypothesis that the population correlation coefficients are equal. However, it is well known that Pearson's correlation is not robust. Even a single outlier can have a substantial impact on Pearson's correlation, resulting in a misleading understanding about the strength of the association among the bulk of the points. A way of mitigating this concern is to use a correlation coefficient that guards against outliers, many of which have been proposed. But apparently there are no results on how to compare dependent robust correlation coefficients when there is heteroscedasicity. Extant results suggest that a basic percentile bootstrap will perform reasonably well. This paper reports simulation results indicating the extent to which this is true when using Spearman's rho, a Winsorized correlation or a skipped correlation.     

Hope and Optimism: Latent Structures and Influences on Grade Expectancy and Academic Performance

ABSTRACT A synthesized model of trait hope ( Snyder 1994, 2002 ) and trait optimism ( Scheier & Carver, 1985 ) is proposed. In this model hope and optimism are conceptualized as facets of an overarching trait called goal attitude. Structural equation modeling is used to test the plausibility of the proposed model in a sample of 345 students in a university psychology course who completed the Adult Hope Scale ( Snyder et al., 1991 ) and the Life Orientation Test–Revised ( Scheier, Carver, & Bridges, 1994 ). The proposed model shows acceptable fit to the observed data. The synthesized model is used to examine the unique and common influences of hope and optimism on grade expectancy and academic performance in 312 students who completed the course. The results show that hope uniquely influenced students' grade expectancies, whereas optimism did not. In turn, grade expectancies influenced academic performance. Neither hope nor optimism had a unique, direct influence on academic performance. In contrast, the shared aspect of hope and optimism (i.e., goal attitude) had a direct influence on academic performance.     

A review of exact hypothesis testing procedures (and selection techniques) that control power regardless of the variances

When testing hypotheses, two important problems that applied statisticians must consider are whether a large enough sample was used, and what to do when the frequently adopted homogeneity of variance assumption is violated. The first goal in this paper is to briefly review exact solutions to these problems. In the one-way ANOVA, for example, these procedures tell an experimenter whether enough observations were sampled so that the power will be at least as large as some pre-specified level. If too few observations were sampled, the procedure indicates how many more observations are required. The solution is exact, which is in contrast to another well-known procedure described in the paper. Also, the variances are allowed to be unequal. The second goal is to review how the techniques used to test hypotheses have also been used to solve problems in selection.     

Sex differences in developmental trends of suicide ideation, plans, and attempts among European American adolescents

Although suicide ideation, plans, and attempts increase during adolescence, it remains unclear whether boys' and girls' risk for these outcomes peaks at different ages. We used longitudinal categorical data (never, once, 2+ times) from the Family Transitions Project (N = 1,248 rural European Americans, ages 11-19) to investigate whether yearly prevalence rates of adolescent suicidal episodes follow different patterns by sex. Multiple-group growth models revealed that peak levels of past-year ideation and plans occurred during mid adolescence for girls, but slowly increased through late adolescence for boys. We found that prevalence patterns for attempts were very similar for boys and girls, with both increasing through mid adolescence and then declining, although girls' risk declined slightly more rapidly. This information may help alert gatekeepers to developmental periods during which boys and girls are particularly vulnerable to suicide-related experiences, and also may help inform the timing of preventive efforts.     

Differential Item Functioning on Antisocial Behavior Scale Items for Adolescents and Young Adults from Single-Parent and Two-Parent Families

We investigated measurement equivalence in two antisocial behavior scales (i.e., one scale for adolescents and a second scale for young adults) by examining differential item functioning (DIF) for respondents from single-parent (n = 109) and two-parent families (n = 447). Even though one item in the scale for adolescents and two items in the scale for young adults showed significant DIF, the two scales exhibited non-significant differential test functioning (DTF). Both uniform and nonuniform DIF were investigated and examples of each type were identified. Specifically, uniform DIF was exhibited in the adolescent scale whereas nonuniform DIF was shown in the young adult scale. Implications of DIF results for assessment of antisocial behavior, along with strengths and limitations of the study, are discussed.     

Support for religio-political aggression among teenaged boys in Gaza: part II: neuroendocrinological findings

Hormones seem to play important roles in the regulation of human aggression. Multiple studies have confirmed that testosterone (T) levels exhibit complex relationships with aggression, dominance, and/or risk-taking behavior. Some evidence suggests that cortisol (CORT) interacts with T and may also be associated with aspects of mood and aggression. However, almost no research to date has investigated the possibility that these neuroendocrine factors are associated with variations in political attitudes or with political aggression. During the second intifada, we tested the hypothesis that morning salivary T and/or salivary CORT levels might be associated with self-rated aggression or with support for religio-political aggression (RPA) among 14-year-old Palestinian boys living in Gaza. We obtained and averaged weekly 09:00 hr salivary measures of T and CORT for more than 1 month. Averaged morning T levels did not correlate with self-rated aggression, but were positively associated with agreement with the statement "religious ends justify any means," (r = .355, P = .014) and marginally associated with a composite measure of support for RPA (r = .247, P = .094). Average CORT levels were inversely correlated with self-rated aggression (r = -.328, P = .037) and with anger (r = -.373, P = .016), but CORT levels were not associated with support for RPA or with the statement "religious ends justify any means." Acknowledging that a modest sample size and methodological issues necessarily limit confidence in our conclusions, these results may represent the first findings regarding neurobiological correlates of support for political aggression.