Parallel analysis (PA) is an often-recommended approach for assessment of the dimensionality of a variable set. PA is known in different variants, which may yield different dimensionality indications. In this article, the authors considered the most appropriate PA procedure to assess the number of common factors underlying ordered polytomously scored variables. They proposed minimum rank factor analysis (MRFA) as an extraction method, rather than the currently applied principal component analysis (PCA) and principal axes factoring. A simulation study, based on data with major and minor factors, showed that all procedures consistently point at the number of major common factors. A polychoric-based PA slightly outperformed a Pearson-based PA, but convergence problems may hamper its empirical application. In empirical practice, PA-MRFA with a 95% threshold based on polychoric correlations or, in case of nonconvergence, Pearson correlations with mean thresholds appear to be a good choice for identification of the number of common factors. PA-MRFA is a common-factor-based method and performed best in the simulation experiment. PA based on PCA with a 95% threshold is second best, as this method showed good performances in the empirically relevant conditions of the simulation experiment.

Background: Compared to typically developing individuals, individuals with attention-deficit-hyperactivity disorder (ADHD) are on average more often exposed to stressful conditions (e.g., school failure, family conflicts, financial problems). We hypothesized that high exposure to stress relates to a more persistent and complex (i.e., multi-problem) form of ADHD, while low-stress exposure relates to remitting ADHD over the course of adolescence. Method: Longitudinal data (ages 11, 13, 16, and 19) came from the Tracking Adolescents’ Individual Life Survey (TRAILS). We selected children diagnosed with ADHD (n = 244; 167 males; 77 females) from the TRAILS clinical cohort and children who screened positive (n = 365; 250 males; 115 females) and negative (gender-matched: n = 1222; 831 males; 391 females) for ADHD from the TRAILS general population sample cohort (total n = 1587). Multivariate latent class growth analysis was applied to parent- and self-ratings of stress exposure, core ADHD problems (attention problems, hyperactivity/impulsivity), effortful control, emotion dysregulation (irritability, extreme reactivity, frustration), and internalizing problems (depression, anxiety, somatic complaints). Results: Seven distinct developmental courses in stress exposure and psychopathology were discerned, of which four related to ADHD. Two persistent ADHD courses of severely affected adolescents were associated with very high curvilinear stress exposure peaking in mid-adolescence: (1) Severe combined type with ongoing, severe emotional dysregulation, and (2) combined type with a high and increasing internalization of problems and elevated irritability; two partly remitting ADHD courses had low and declining stress exposure: (3) inattentive type, and (4) moderate combined type, both mostly without comorbid problems. Conclusions: High-stress exposure between childhood and young adulthood is strongly intertwined with a persistent course of ADHD and with comorbid problems taking the form of either severe and persistent emotion dysregulation (irritability, extreme reactivity, frustration) or elevated and increasing irritability, anxiety, and depression. Conversely, low and declining stress exposure is associated with remitting ADHD and decreasing internalizing and externalizing problems. Stress exposure is likely to be a facilitating and sustaining factor in these two persistent trajectories of ADHD with comorbid problems into young adulthood. Our findings suggest that a bidirectional, continuing, cycle of stressors leads to enhanced symptoms, in turn leading to more stressors, and so forth. Consideration of stressful conditions should, therefore, be an inherent part of the diagnosis and treatment of ADHD, to potentiate prevention and interruption of adverse trajectories.

In emotion dynamic research, one distinguishes various elementary emotion dynamic features, which are studied using intensive longitudinal data. Typically, each emotion dynamic feature is quantified separately, which hampers the study of relationships between various features. Further, the length of the observed time series in emotion research is limited and often suffers from a high percentage of missing values. In this article, we propose a vector autoregressive Bayesian dynamic model that is useful for emotion dynamic research. The model encompasses 6 elementary properties of emotions and can be applied with relatively short time series, including missing data. The individual elementary properties covered are within-person variability, innovation variability, inertia, granularity, cross-lag regression, and average intensity. The model can be applied to both univariate and multivariate time series, allowing one to model the relationships between emotions. One may include external variables and non-Gaussian observed data. We illustrate the usefulness of the model on data involving 50 participants self-reporting on their experience of 3 emotions across the period of 1 week using experience sampling. (PsycINFO Database Record