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.     

Effect of tDCS on Fine Motor Control of Patients in Subacute and Chronic Post-Stroke Stages

Abstract

In this study we compared the effects of transcranial direct current stimulation (tDCS) in the subacute and chronic stages of post-stroke recovery. Anodal/sham tDCS was applied to the primary motor cortex of stroke patients in these stages of recovery in a cross-over design. The Jebsen–Taylor hand function test was employed. The repeated-measure ANOVA showed significant influence of the stimulation type and test performance time (during/after tDCS) with no overall influence of recovery stage. The interaction TYPE*TIME*STAGE was significant. The effect after anodal tDCS in the subacute stage was significantly higher compared to the effects in all relevant conditions including the chronic stage. Therefore, tDCS treatment in the subacute stage of recovery can be superior, at least for some patients, to treatment in the chronic stage.     

Please accept my sincere and humble apologies: The HEXACO model of personality and the proclivity to apologize

We investigated the links of the HEXACO personality factors and facets with the proclivity to apologize for transgressions, using self- and observer-reports of personality in two adult samples. The proclivity to apologize showed its strongest correlations with the honesty–humility factor, whether evaluated by the self or a knowledgeable observer. Agreeableness was a positive correlate of the proclivity to apologize in one sample only. In both samples, self-reported conscientiousness was positively associated with a proclivity to apologize. We also obtained self-reports on the guilt and shame proneness scales, given the strong conceptual link between guilt and apology. The proclivity to apologize was associated positively with facets of guilt (especially Negative Behavior Evaluation) but negatively with one facet of Shame (Withdrawal).     

Associations between young adult romantic relationship quality and problem behaviors: An examination of personality–environment interactions

This longitudinal study examined person–environment interplay by testing interaction effects between adolescent personality type (i.e., overcontrollers, undercontrollers, and resilients) and young adult romantic relationship quality on young adult delinquency and anxiety. The study employed six waves of longitudinal questionnaire data collected across 10 years from Dutch youths. Results showed that support from romantic partner was related to a relatively stronger decrease in anxiety in young adulthood for overcontrollers than for resilients. Moreover, higher negative interaction with romantic partner was related to a relative increase in delinquent behaviors for undercontrollers, while no such links emerged for overcontrollers and resilients. This study highlights the importance of considering the interplay between personality characteristics and environmental–relational factors when examining young adults’ developmental outcomes.     

Does integral affect influence intentions to use artificial intelligence for skin cancer screening? A test of the affect heuristic

Objective: This study investigated how affect influences people’s processing of messages about risks and benefits of using autonomous artificial intelligence (AI) technology to screen for skin cancer. We examined integral affect (emotion derived during decision making) separately from incidental affect (extraneous mood states).

Design: Using the affect heuristic framework, we randomly assigned 273 participants to conditions featuring risk (high, low, uncertain) or benefit (high, low, uncertain) messages about AI. Following ‘affect-as-spotlight’, we also explored whether people’s integral affect towards skin cancer moderated the relationship between risk/benefit messages and AI screening intentions.

Outcomes: Perceived risk, perceived benefit, positive and negative affect toward AI, intention to use AI screening.

Results: After controlling for incidental affect and risk perceptions, we found that compared to low risk messages, uncertain risk messages increased participants’ negative affect toward AI, decreased positive affect toward AI, increased AI risk evaluations and reduced AI benefit evaluations. Perceptual variables significantly mediated participants’ intentions to use AI for risk messages but not benefit messages. No moderation effects were found.

Conclusions: Results suggest extending the affect heuristic framework to include uncertain risk conditions. Integral AI affect influenced people’s interpretation of messages, which then impacted likelihood to use AI technology for health.     

Origins of adolescents’ earliest memories

ABSTRACT

This prospective longitudinal study traced changes and individual differences in childhood amnesia over adolescence. A sample of 58 adolescents were followed from age 1-1/2 to age 16 years across 8 timepoints. At ages 12 (n?=?46) and 16 (n?=?51), adolescents completed an early memory interview. Early childhood measures included children’s self-awareness, attachment security, nonverbal memory, verbal memory, language, theory of mind, narrative, and the early reminiscing environment (mothers’ elaborative reminiscing). Adolescents continued to forget their earliest memories over adolescence, such that the age of first memory increased from 40 to 52 months from ages 12 to 16. The sole unique contributor to individual differences in age of earliest memory at both 12 and 16 years was mothers’ elaborative reminiscing, with adolescents recalling earlier memories if their mothers had reminisced more elaboratively with them during early childhood. At age 16, the role of maternal reminiscing was moderated by self-awareness at age 1-1/2. Mothers’ elaborative reminiscing mattered for the age of adolescents’ earliest memories only for children who showed lower levels of self-awareness as toddlers. This pattern suggests a buffering effect for the role of maternal reminiscing in children’s earliest memories, and supports integrated theories of childhood amnesia.     

A non-commutative generalization of Łukasiewicz rings

The goal of the present article is to extend the study of commutative rings whose ideals form an MV-algebra as carried out by Belluce and Di Nola [1] to non-commutative rings. We study and characterize all rings whose ideals form a pseudo MV-algebra, which shall be called here generalized Łukasiewicz rings. We obtain that these are (up to isomorphism) exactly the direct sums of unitary special primary rings.