Interaction effects in ANOVA provide crucial insights into how the effect of one independent variable depends on the level of another. However, interpreting these interactions, especially three-way interactions, remains a challenge. Firstly, visualisation techniques typically rely on multiple separate two-dimensional plots conditioned on the levels of a third factor; as the number of levels of the third factor increases, so does the number of plots, complicating interpretation. Secondly, routinely applying uncorrected post-hoc pairwise comparisons oversimplifies interaction effects and, by ignoring the multiplicity of tests, inflates Type I error rates, potentially leading to misleading conclusions. Advanced methods, such as partial dependence plots and interaction decomposition models, have partially addressed these limitations; however, they typically require substantial statistical or computational expertise, which limits their accessibility. To address these challenges, this manuscript introduces EXCITE (Enhanced eXploration of Complex Interactions in ANOVA using Trees), an interactive web application developed using the Shiny package within the R statistical environment. EXCITE integrates traditional two- and three-way ANOVA models with decision tree-based visualisations. Decision trees detect interaction patterns via recursive data partitioning and present conditional subgroup relationships through an interpretable tree structure. The advantages of EXCITE include presenting two- and three-way interactions intuitively, enhancing accessibility, and facilitating accurate interpretation of complex statistical interactions. This integration provides researchers and educators across various scientific disciplines with a user-friendly tool for interpreting and visualising ANOVA interactions. We illustrate the capabilities of EXCITE using both simulated examples and a real dataset to demonstrate its practical applicability. The web application is freely available online, requiring no installation or coding expertise, at https://zq9mvv-vub0square.shinyapps.io/EXCITE-research-tool/ .

OBJECTIVES: This study investigates the association between precarious employment (PE) and mental well-being and examines the mediating role of five intrinsic quality of work (IQW) dimensions: autonomy, physical demands, work intensity, skill discretion, and social support. We distinguish between main (>24 hours/week) and supplementary (≤24 hours/week) gig workers. METHODS: Survey data from 397 Belgian gig workers were used to construct a multidimensional, gig-specific measure of PE (the Employment Precariousness Scale for gig work: ‘EPRES-gw’). Structural equation modeling was applied to test mediation by IQW dimensions and examine differences between main and supplementary gig workers. RESULTS: PE was positively associated with poor mental well-being among main but not supplementary workers. Among main gig workers, the relationship was mediated by high work intensity, physical demands, and low social support. For supplementary workers, low autonomy mediated the association. CONCLUSION: PE is particularly relevant for the mental well-being of main gig workers. The role of IQW is important, though the key dimensions differ by time spent in in gig work. These findings highlight the need for policy interventions and research addressing both employment rights and IQW-related psychosocial risks, with approaches tailored to the distinct challenges of main versus supplementary gig workers.

The study of dyadic data has become essential to understanding family relationships. While directed dyadic data capture a person's relationship to a partner, resulting in two scores per dyad, undirected dyadic data measure something that is common to two people using a single score, for example, the distance two people stand from each other while conversing. This article introduces a modification of the family social relations model specifically developed for undirected data, a new framework to analyze undirected data for distinguishable dyad members. The model allows researchers to determine the contribution of individual-, dyadic-, and family-level components on undirected measures. We illustrate the model using data on shared family meals among dyad members in 99 two-parent two-child families. The analysis reveals that factors at all three levels of analysis determine how often two family members share a meal, but characteristics of the family as a group are most important. We also introduce an innovative approach to estimating the family factor, one that allows different dyadic scores to be affected differently by the family climate. Finally, we introduce an online app that implements the analysis of the family social relations model for undirected data, minimizing the need for confirmatory factor analysis skills. (PsycInfo Database Record (c) 2026 APA, all rights reserved).

The frustration of relational needs is a common source of conflict in romantic relationships. Empathic accuracy (EA) defined as the ability to accurately perceive and understand a partner's thoughts and feelings plays a key role in resolving these conflicts. In this study, we tested the hypothesis that need frustration and EA are associated both within individuals and between romantic partners during actual conflict interactions. Data were analyzed from a lab-based conflict interaction study conducted in 2014, which included a video-mediated recall task. Results from two cross-sectional actor-partner interdependence models revealed that women's EA was positively associated with their male partner's need frustration at the start of the conflict, but this association was no longer present by the end. Additionally, women's EA was marginally negatively associated with their own need frustration at both the start and end of the conflict interaction. These findings highlight the complex and dynamic nature of the relationship of need frustration and EA during couples' actual conflict interactions. Further research is needed to explore the underlying mechanisms driving these associations over time. (PsycInfo Database Record (c) 2026 APA, all rights reserved).

In China, debates on achieving work-family balance have intensified with the rise of the dual-earner model. Balancing paid and unpaid work is stressful for dual-earner couples resulting in poor mental well-being outcomes for both partners. While prior mental well-being research mainly focused on individual associations, our study investigates associations of paid and unpaid workloads on spousal mental well-being within married dyads. Moreover, given that family support is an important resource in accordance with Chinese cultural and social norms, we investigate the mitigating role of family support within this dyadic relationship. Using coupled data from the Chinese Family Panel Study (CFPS) Wave 5, we employed Actor-Partner Interdependence Model (APIM) to explore crossover mechanisms of multiple workloads (total, paid, and unpaid) and spousal mental well-being. Mental well-being was evaluated by utilizing a scale for depressive symptoms and for subjective well-being. We found that both genders’ higher levels of depression were border-significantly related to their own total workload (i.e. the sum of paid and unpaid labour), yet spousal associations were unobserved. For women, paid workload is negatively associated with subjective well-being while controlling for unpaid workload. The moderation models revealed, for men, that family support received from their wives’ family attenuates the positive association between workloads and depression. Our study advances our knowledge of the gender dynamics influencing work-family balance and strengthens the rationale for the adoption of family-friendly workplace regulations in China.

Linear regression is a key statistical method for exploring relationships between a continuous outcome and predictors. Ensuring its assumptions are met is vital for accurate estimates and valid p-values. However, misconceptions about these assumptions, especially among non-statisticians, still exist and often hinder proper diagnostics. To address this challenge, we developed ReDiag, an interactive Shiny web application designed to assist researchers in assessing the normality, homoscedasticity, and linearity assumptions and handle violations effectively. ReDiag’s source code and an extensive tutorial applied to two example published datasets are available on GitHub. The app can be accessed via shinyapps.io.

As plans for deep space and long-duration missions advance, research in space and space-analog environments is becoming an urgent scientific priority. However, this type of fieldwork poses a unique set of challenges. The development of research methodologies and designs cannot rely on broad evidence base and thus requires scientific judgment and multidisciplinary psychophysiological expertise. Most studies comprise small samples, often lack control groups, sex differences have seldom been directly tested in this area and inter-individual variability is prevalent in this population. Moreover, this research domain is characterized by several exceptional factors that must be addressed. The target population is highly trained and not representative of the general population, demanding adapted study designs and highly sensitive and operationally relevant research tools. To avoid overburdening the already heavy operational schedules of this population, a careful and feasible balance must be established between scientific data quality and acceptable monitoring load. Furthermore, several issues of location, timing, and type of baseline measures must be explicitly considered, while long-term follow-up designs are necessary to assess both recovery and persistent post-mission effects. Major space agencies have indeed identified methodological issues as a knowledge gap in this area. In this review, we provide an overview of these methodological challenges unique to space life sciences and offer solutions where possible. We argue that space research remains feasible despite these constraints, but only when it is approached with the understanding that such fieldwork often requires fundamentally different methods than traditional laboratory science.

Medication use is increasing in psychiatric populations, particularly those with personality disorders (PDs). Older adults with PDs are at higher risk for adverse drug reactions (ADRs), which may interfere with daily functioning. This study aimed to describe medication use and health-related quality of life (HR-QOL) in older adults with PDs compared with control groups and to evaluate predictors of medication use and HR-QOL. The PhArmacotherapy aND pOlypharmacy in oldeR Adults (PANDORA) study is a Dutch multicenter cross-sectional study including 77 older adults with PDs (OA-PD), 54 younger to middle-aged adults with PDs (A-PD), and 88 healthy older adults (OA-H). Medication use was assessed via participant questionnaires and verified against electronic health records for patients. HR-QOL was measured using the EQ-5D-3L (visual analog scale [VAS] and utility score). Statistical analyses were performed with general linear models. Polypharmacy (≥ 5 medications daily) was present in 55.8

ObjectiveThis paper proposes using the Social Relations Model to grasp functional solidarity in families with adolescent and emerging adult children.BackgroundFamily solidarity is a framework for understanding cohesion among family members. Essential to this concept is commitment to each other's well-being and a willingness to support one another. The majority of functional solidarity research focuses on support transfers between adult children and older parents. Existing measures do not account for the intra- and intergenerational perspectives of younger families.MethodsWe created a concise round-robin instrument for three dimensions of functional solidarity: willingness to provide financial, practical, and emotional support. It was tested with 586 Belgian parents and adolescents in step-, nuclear-, and single-parent families. As a motivating example, we unraveled the individual, dyadic, and family components contributing to emotional support willingness in 81 stepfamilies.ResultsSocial relations analysis showed that biological parents substantially contributed to the average levels of attitudinal emotional functional solidarity. The relative variance decomposition revealed that individual characteristics were the largest source of between-family differences, followed by family members' unique relationships, especially with stepparents. We found dyadic reciprocity in horizontal relationships: dyad members who were especially willing to provide emotional support were more likely to have a supportive partner or sibling.ConclusionOverall, this paper opens up opportunities for family researchers to use the Social Relations Model to examine family solidarity dynamics.

The correct specification of covariance structures in linear mixed models (LMMs) is critical for accurate longitudinal data analysis. These data, characterised by repeated measurements on subjects over time, demand careful handling of inherent correlations to avoid biased estimates and invalid inferences. Incorrect covariance structure specification can lead to inflated type I error rates, reduced statistical power, and inefficient estimation, ultimately compromising the reliability of statistical inferences. Traditional methods for selecting appropriate covariance structures, such as AIC and BIC, often fall short, particularly as model complexity increases or sample sizes decrease. Studies have shown that these criteria can misidentify the correct structure, resulting in suboptimal parameter estimates and poor assessment of standard errors for fixed effects. Additionally, relying on trial-and-error comparisons in LMMs can lead to overfitting and arbitrary decisions, further undermining the robustness of model selection and inference. To address this challenge, we introduce LiMMCov, an interactive app that uniquely integrates time-series concepts into the process of covariance structure selection. Unlike existing tools, LiMMCov allows researchers to explore and model complex structures using autoregressive models, a novel feature that enhances the accuracy of model specification. The app provides interactive visualisations of residuals, offering insights into underlying patterns that traditional methods may overlook. LiMMCov facilitates a systematic approach to covariance structure selection with a user-friendly interface and integrated theoretical guidance. This paper details the development and features of LiMMCov, demonstrates its application with an example dataset, and discusses its potential impact on research. The app is freely accessible at https://zq9mvv-vub0square.shinyapps.io/LiMMCov-research-tool/.

Across the lifespan, suicide mortality rates are highest among older adults, yet research on self-harm in later life remains limited. This study explores how self-reported maladaptive personality traits (measured by the PID-5-BF+M) are associated with self-harm in older adults, and whether there are potential differences according to the type of self-harm behaviors (indirect, direct, and the co-occurrence of these two) in this age group. From a convenience sample of 790 adults aged 60 years and older, 102 participants were selected using a matched-pair design. Regression models showed that three personality domains (i.e., Negative Affectivity, Antagonism, and Psychoticism) and eight personality facets were related with self-harm in older adults. Boxplots showed differences between maladaptive personality scores depending on self-harm type. Presence of elevated PID-5-BF+M scores may help clinicians identify elevated self-harm risk in older adults. Future research should differentiate between types of self-harm, as the associated risk factors may vary.

Though perioperative pain neuroscience education (PPNE) positively influences patients' surgical outcomes, little is known about the mechanisms behind this treatment's success. Therefore, this study aims to evaluate the potential mediating role of pain cognitions and pain sensitivity in the treatment effect of PPNE on postoperative quality of life in people undergoing surgery for lumbar radiculopathy. This secondary analysis uses data from 120 participants of a randomized controlled trial who were randomized to receive either PPNE or perioperative biomedical education before undergoing surgery for lumbar radiculopathy. Quality of life was assessed 1-year postsurgery using the short form 36-item health survey (SF36) physical and mental component scores. Potential mediators included pain cognitions (ie, kinesiophobia, pain catastrophizing, and hypervigilance) and pain sensitivity (ie, endogenous nociceptive modulation), assessed 6 weeks postsurgery. Mediation models were constructed using structural equation modeling, and 95% confidence intervals (CIs) were calculated using 10,000 bootstrap samples. Analyses show a significant total effect for PPNE (estimate = .464, 95% CI [.105, .825]) and a significant indirect effect via pain catastrophizing on the SF36 physical component (estimate = .124, 95% CI [.001, .293]). No mediating effect was found through the remaining pain cognitions or pain sensitivity measures. Also, no potential mediators were identified for the treatment effect of PPNE on the SF36 mental component. Our findings suggest that pain catastrophizing mediates the treatment effect of PPNE on physical health-related quality of life in people undergoing surgery for lumbar radiculopathy. PERSPECTIVE: This secondary analysis identified pain catastrophizing as a mediator for PPNE in people undergoing surgery for lumbar radiculopathy. More so, its findings indicate that this educational intervention can enhance the postoperative physical health-related quality of life of these patients by addressing their catastrophizing thoughts. TRIAL REGISTRATION: Clinicaltrials.gov (NCT02630732).

Foster children often experienced adversities, putting them at risk for problematic outcomes ( Dozier & Rutter, 2016 ). To our knowledge, there is no research regarding the cognitive and language development of young Flemish foster children. In this study, we describe a study conducted longitudinal research over a one year period into the development of 53 young foster children (12–20 months old at T1). The cognitive and language development of the children was measured using the Bayley Scales of Infant and Toddler Development-Third-Edition (Bayley-III-NL). First, scaled scores of the Bayley subscales cognitive functioning, receptive language and expressive language, both at T1 and T2, were compared to the mean norm-scores. Second, the associated variables with the children’s functioning on cognitive and language scales were explored using Multilevel Modelling. For all subscales except receptive language at T2, the results did not significantly differ from the mean normative scores. The scores of the foster children in this study were significantly lower on receptive language at T2. When we looked at individual scores, most children (66%–83%) had scores that did not differ more than one standard deviation from the normative mean. Children in kinship foster care had lower scores in multiple developmental domains. There were also negative associations between both language subscales and insecure attachment behavior. For most subscales, the results did not significantly differ from the mean normative scores, which is promising.

Foster children are at risk for developing disorganized attachment relationships (Van den Dries et al., 2009; Vasileva & Petermann, 2018) and behavioural problems (Goemans et al., 2015; Vanschoonlandt et al., 2012). Video-feedback Intervention to promote Positive Parenting and Sensitive Discipline – Foster Care/Adoption (VIPP-FC/A) is an intervention aimed at improving sensitive parenting in order to promote secure attachment relations and reduce behavioural problems. In this study, a Randomized Controlled Trial (RCT) was used in order to examine the effectiveness of VIPP-FC/A in a Flemish foster care sample ( n = 100), using questionnaires at three measurement moments. The hypothesis was that VIPP-FC/A would increase foster mothers’ sensitive parenting and decrease the externalizing behavioural problems and insecure attachment behaviour of the foster children and parenting stress of the foster mothers. The intervention effects on these four outcome variables were analysed by constructing four multilevel models. After controlling for the baseline measurement, there was no significant main effect of condition for sensitive parenting, externalizing problems, insecure attachment behaviour and parenting stress. There was however a significant effect of condition and age on insecure attachment behaviour: within the group of youngest foster children (under 30 months), children in the intervention group scored lower insecure attachment scores than children in the control group. Additionally, there was a significant effect of condition and type of foster care on externalizing behaviour problems. In the group of children placed in kinship foster care, children in the intervention group had lower external behavior scores than children in the control group.

Selection and training of special operations forces operators is long-lasting process that involves significant manpower to select the best candidates for one of the most demanding and dangerous jobs in the world. The Tier 1 qualification course, which represents the initial months of training for an operator, is so labor-intensive that even after completing a specific selection course to reduce the number of failures, attrition remains the highest among all military trainings. This study presents data of 77 successfully selected candidates to the special forces qualification course in Belgium and investigates the differences between succeeders (n = 16) and dropouts (n = 61). Unlike previous investigations, these results do not describe successfully selected candidates for the training, rather successful operators. Additionally, previous studies have primarily focused on physical fitness as the performance outcome to identify relevant subcomponents such as aerobic capacity, muscular strength, or power. By contrast, the present article provides a detailed investigation of the performance profile at not only the physical level, but also cognitive and personality levels for among succeeders and dropouts in the qualification course. Unsurprisingly, physical fitness was a significant difference between groups, and a major predictor of success. However, for the first time, we demonstrate the major influence of intelligence (measured as intelligence quotient), as the most important determinant of success for the qualification course, according to a relative weight analysis. In addition, the detailed intellectual assessment shows that some visuospatial measures are less relevant for success, whereas verbal measures are highly relevant, and may have been overlooked in previous literature.

OBJECTIVES:The aim of this systematic review and meta-analysis is to assess the prevalence of loneliness in many countries worldwide which have different ways of assessing it. DESIGN:Systematic review and meta-analysis. SETTING:We searched seven electronic databases for English peer-reviewed studies published between 1992 and 2021. PARTICIPANTS:We selected English-language peer-reviewed articles, with data from non-clinical populations of community-dwelling older adults (>60 years), and with "loneliness" or "lonely" in the title. MEASUREMENTS:A multilevel random-effects meta-analysis was used to estimate the prevalence of loneliness across studies and to pool prevalence rates for different measurement instruments, data collection methods, and countries. RESULTS:Our initial search identified 2,021 studies of which 45 (k = 101 prevalence rates) were included in the final meta-analysis. The estimated pooled prevalence rate was 31.6% (n = 168,473). Measurement instrument was a statistically significant moderator of the overall prevalence of loneliness. Loneliness prevalence was lowest for single-item questions and highest for the 20-item University of California-Los Angeles Loneliness Scale. Also, differences between modes of data collection were significant: the loneliness prevalence was significantly the highest for face-to-face data collection and the lowest for telephone and CATI data collection. Our moderator analysis to look at the country effect indicated that four of the six dimensions of Hofstede also caused a significant increase (Power Distance Index, Uncertainty Avoidance Index, Indulgence) or decrease (Individualism) in loneliness prevalence. CONCLUSIONS:This study suggests that there is high variability in loneliness prevalence rates among community-dwelling older adults, influenced by measurement instrument used, mode of data collection, and country.

Mid-March 2020, Belgium went in lockdown to combat the COVID-19-pandemic. Having to provide school-based day care and adapt to online teaching, while all social, cultural and sports events and activities were cancelled, secondary school teachers’ physical activity (PA) and sedentary behaviour (SB) may have been affected considerably. This study investigates the impact of the first Belgian lockdown on PA and SB in Flemish secondary school teachers. This prospective cohort study was conducted throughout the 2019–2020 school year. PA and SB measured in March/April 2020 were compared with a pre-lockdown measurement in January/February 2020. Other pre-lockdown measurements (September/October 2019 and November/December 2019) and one other during-lockdown measurement (May/June 2020) allowed us to control for confounding. Validated questionnaires were used to assess participants’ PA and SB. Generalized linear mixed models were applied in R. Among 624 participants (77·2

ObjectivesSevere posttraumatic stress disorder (PTSD) in older adults (>= 60 years) has been found to be associated with maladaptive personality functioning and personality disorders (PD). Emerging evidence in adults supports that reprocessing adverse events with Eye Movement Desensitization and Reprocessing (EMDR) could improve personality functioning and reduce full PDdiagnosis.MethodsA multicenterfeasibilitystudy in 24 older PTSD-patients receiving weekly EMDR-sessions for either 3, 6 or 9 months. A linear-mixed-model was used with personality functioning (SIPP-SF) as dependent variable and time, PTSD-severity (CAPS-5), and "othertreatment" as predictor variables. Secondary, pre- and posttreatment percentages were calculated for the PDspresence.ResultsSymptom changes over time showed a significant influence of CAPS-5 on SIPP-SF (b = -1.40, 95% CI=[-2.48 to -0.33], p = .012), no significant effect of time for total SIPP-SF, and a significant improvement of SIPP-SF "identityintegration"-scale over time (b = 9.20, 95% CI=[0.97-17.42], p = .029). There was a marginal significant effect of "othertreatment" (b = 8.42, 95% CI=[-0.30-17.13], p = .058). There was 31% full PDs-decrease.ConclusionsObserved improvements in personality functioning from pre to post EMDRtreatment were explained by PTSD-severity. Identityintegration improved significantly over time. Results suggest that participants with "othertreatment" showed more severe baseline-pathology and thus lower personality functioning.Clinical implicationsEMDR, in addition to being a feasible treatment option for older adults with PTSD, improves personality functioning and reduces the presence of PDs over time.'

Introduction:Little is known on how diet, physical activity (PA) and sedentary behavior (SB) changes during pregnancy and after childbirth in primiparous couples. Moreover, it is unclear how potential behavioral changes are associated with changes in BMI. This study examined changes in diet, PA and SB, and their association with changes in BMI in couples transitioning to parenthood.Methods:Dietary intake (FFQ), PA, SB (both Actigraph GT3X accelerometers) and BMI of women and men were assessed at 12 weeks of gestation, 6 weeks and 6 months postpartum. Data were analyzed using dyadic longitudinal data analyses techniques.Results:In women, a decrease in fruit intake, an increase in alcohol intake, an increase of light-intensity PA, and a decrease in SB were observed from the beginning of pregnancy up to 6 months postpartum. Decreases in fruit intake between 6 weeks and 6 months postpartum was associated with increases in BMI. Men did not show significant dietary changes, while an increase in light-intensity PA and a decrease in moderate-to-vigorous PA (MVPA) was observed at 6 months postpartum when compared to 12 weeks of gestation. Paternal increases in "avoidance food group" intake were associated with increases in BMI between baseline and 6 weeks postpartum. No associations of changes in BMI and changes in PA and SB were found.Discussion:Not only mothers but also fathers experienced unfavorable changes in lifestyle during the transition to parenthood, with impact on BMI changes. This highlights the need to monitor unhealthy changes in lifestyle and body weight in both parents when expecting a child and after childbirth.Clinical trial registration:Clinicaltrials.gov, NCT03454958.

COVID-19 can induce neurological sequelae, negatively affecting the quality of life. Unravelling this illness's impact on structural brain connectivity, white-matter microstructure (WMM), and cognitive performance may help elucidate its implications. This cross-sectional study aimed to investigate differences in these factors between former hospitalised COVID-19 patients (COV) and healthy controls. Group differences in structural brain connectivity were explored using Welch-two sample t-tests and two-sample Mann-Whitney U tests. Multivariate linear models were constructed (one per region) to examine fixel-based group differences. Differences in cognitive performance between groups were investigated using Wilcoxon Rank Sum tests. Possible effects of bundle-specific FD measures on cognitive performance were explored using a two-group path model. No differences in whole-brain structural organisation were found. Bundle-specific metrics showed reduced fiber density (p=0.012, Hedges' g=0.884) and fiber density cross-section (p=0.007, Hedges' g=0.945) in the motor segment of the corpus callosum in COV compared to healthy controls. Cognitive performance on the motor praxis and digit symbol substitution tests was worse in COV than healthy controls (p<0.001, r=0.688; p=0.013, r=422, respectively). Associations between the cognitive performance and bundle-specific FD measures differed significantly between groups. WMM and cognitive performance differences were observed between COV and healthy controls.