The Performance of Multivariate Methods for Two-Group Comparisons with Small Samples and Incomplete Data

Abstract

In intervention studies having multiple outcomes, researchers often use a series of univariate tests (e.g., ANOVAs) to assess group mean differences. Previous research found that this approach properly controls Type I error and generally provides greater power compared to MANOVA, especially under realistic effect size and correlation combinations. However, when group differences are assessed for a specific outcome, these procedures are strictly univariate and do not consider the outcome correlations, which may be problematic with missing outcome data. Linear mixed or multivariate multilevel models (MVMMs), implemented with maximum likelihood estimation, present an alternative analysis option where outcome correlations are taken into account when specific group mean differences are estimated. In this study, we use simulation methods to compare the performance of separate independent samples t tests estimated with ordinary least squares and analogous t tests from MVMMs to assess two-group mean differences with multiple outcomes under small sample and missingness conditions. Study results indicated that a MVMM implemented with restricted maximum likelihood estimation combined with the Kenward–Roger correction had the best performance. Therefore, for intervention studies with small N and normally distributed multivariate outcomes, the Kenward–Roger procedure is recommended over traditional methods and conventional MVMM analyses, particularly with incomplete data.     

Values of Children, Parent–Child Relationship, and Social Change in Korea: Indigenous, Cultural, and Psychological Analysis

Les recherches sur les valeurs que les parents attribuent aux enfants se demandent pourquoi les gens décident ou non d’avoir des enfants et s’intéressent au nombre d’enfants qu’ils choisissent d’avoir. On décrit dans la première partie de cet article la relation parents‐enfants traditionnelle, la structure familiale et les changements sociaux qui se sont produits ces cinquante dernières années en Corée du sud. On présente dans la deuxième partie les résultats de l’étude de 1972 sur les valeurs attribuées aux enfants réalisée en Corée du sud (Lee & Kim, 1975). Dans la dernière partie, on expose une recherche empirique sud‐coréenne portant sur un échantillon de 314 jeunes mères et 395 mères plus âgées. Il apparaît que les bénéfices psychologiques sont les raisons majeures qui justifient le choix d’avoir un enfant et que les contraintes personnelles et financières sont les motifs dominants de ne pas en avoir. Ces résultats mettent en défaut les modèles économiques et utilitaires et soulignent l’importance des facteurs psychologiques, relationnels et culturels. Research on parents’ attribution of value to children examines why people decide to have children or not and the number of children they choose to have. In the first part of this paper, the traditional parent–child relationship, family structure, and social changes that have occurred in South Korea during the past 50 years are reviewed. In the second section, the results of the 1972 Values of Children Study conducted in South Korea ( Lee & Kim, 1975 ) are reviewed. In the final section, an empirical study conducted in South Korea with a sample of 314 young mothers and 395 older mothers is reported. The results indicate that psychological benefits are the most important reasons for having a child and personal and financial constraints are the most important reasons for not having a child. These results challenge the economic and utilitarian models and suggest the importance of understanding the psychological, relational, and cultural factors.     

Surfing the implicit wave

Implicit learning was investigated in two experiments involving a complex motor task. Participants were required to balance on a stabilometer and to move the platform on which they were standing to match a constantly changing target position. Experiment 1 examined whether a segment (middle third) that was repeated on each trial would be learned without participants becoming aware of the repetitions (i.e., implicitly). The purpose of Experiment 2 was to determine the relative effectiveness of explicit versus implicit learning. Here, two identical segments were presented on each trial (first and last thirds), with participants only being informed that one segment (either first or last) was repeated. The acquisition results from both experiments indicated large improvements in performance across 4 days of practice, with performance on the repeated segments being generally superior to that on the non-repeated segment. On the retention tests on Day 5, errors on the repeated segment(s) were smaller than those on the random segment(s). Furthermore, in Experiment 2, the errors on the repeated-known segment, although smaller than those on the random segment, were larger than those on the repeated-unknown segment. Interview results indicated that participants were not consciously aware that a segment was repeated unless they were informed. These results suggest that implicit learning can occur for relatively complex motor tasks and that withholding information concerning the regularities is more beneficial than providing this information.     

Predicting Individuals’ Experienced Fear From Multimodal Physiological Responses to a Fear-Inducing Stimulus

Emotions are experienced differently by individuals, and thus, it is important to account for individuals’ experienced emotions to understand their physiological responses to emotional stimuli. The present study investigated the physiological responses to a fear-inducing stimulus and examined whether these responses can predict experienced fear. A total of 230 participants were presented with neutral and fear-inducing film clips, after which they self-rated their experienced emotions. Physiological measures (skin conductance level and response: SCL, SCR, heart rate: HR, pulse transit time: PTT, fingertip temperature: FT, and respiratory rate: RR) were recorded during the stimuli presentation. We examined the correlations between the physiological measures and the participants’ experienced emotional intensity, and performed a multiple linear regression to predict fear intensity based on the physiological responses. Of the participants, 92.5% experienced the fear emotion, and the average intensity was 5.95 on a 7-point Likert scale. Compared to the neutral condition, the SCL, SCR, HR, and RR increased significantly during the fear-inducing stimulus presentation whereas FT and PTT decreased significantly. Fear intensity correlated positively with SCR and HR and negatively with SCL, FT, PTT, and RR. The multiple linear regression demonstrated that fear intensity was predicted by a combination of SCL, SCR, HR, FT, and RR. Our findings indicate that the physiological responses to experiencing fear are associated with cholinergic, sympathetic, and α-adrenergic vascular activation as well as myocardial β-sympathetic excitation, and support the use of multimodal physiological signals for quantifying emotions.     

Experimentelle Untersuchungen über Sinnzusammenhang,Lautgestalt und Wortbedeutung

Ohne Zusammenfassung     

Effect of Socioeconomic Status on the Linkage Between Suicidal Ideation and Suicide Attempts

Previous suicide attempts are a leading risk factor for completed suicide. To identify specific characteristics of those at high risk for attempts, we investigated associations with socioeconomic status (SES). Data from the 2013 Korean Community Health Survey (KCHS) included adults who reported suicidal ideation (N = 220,245). Attempts in the past 12 months were assessed. Associations of demographic, socioeconomic, and suicide‐related behavioral factors were analyzed using multiple logistic regression. Among those with suicidal ideation, 862 (3.9%) had attempted suicide. After stratification by age and gender, results showed that low education and unemployed young adult men and women had significantly higher rates of attempts. The lowest income level was associated with significantly higher rates of attempts in only young adult women. Among those with the lowest and highest income, the association between ideation and attempts was attenuated, whereas it was enhanced among other income groups.