Psychological research often relies on Exploratory Factor Analysis (EFA). As the outcome of the analysis highly depends on the chosen settings, there is a strong need for guidelines in this context. ...Therefore, we want to examine the recent methodological developments as well as the current practice in psychological research. We reviewed ten years of studies containing EFAs and contrasted them with new methodological options. We focused on four major issues: an adequate sample size, the extraction method, the rotation method and the factor retention criterion determining the number of factors. Finally, we present modified recommendations based on these reviewed empirical studies and practical considerations.
Determining the number of factors is one of the most crucial decisions a researcher has to face when conducting an exploratory factor analysis. As no common factor retention criterion can be seen as ...generally superior, a new approach is proposed-combining extensive data simulation with state-of-the-art machine learning algorithms. First, data was simulated under a broad range of realistic conditions and 3 algorithms were trained using specially designed features based on the correlation matrices of the simulated data sets. Subsequently, the new approach was compared with 4 common factor retention criteria with regard to its accuracy in determining the correct number of factors in a large-scale simulation experiment. Sample size, variables per factor, correlations between factors, primary and cross-loadings as well as the correct number of factors were varied to gain comprehensive knowledge of the efficiency of our new method. A gradient boosting model outperformed all other criteria, so in a second step, we improved this model by tuning several hyperparameters of the algorithm and using common retention criteria as additional features. This model reached an out-of-sample accuracy of 99.3% (the pretrained model can be obtained from https://osf.io/mvrau/). A great advantage of this approach is the possibility to continuously extend the data basis (e.g., using ordinal data) as well as the set of features to improve the predictive performance and to increase generalizability.
Translational Abstract
Determining the number of factors is one of the most important decisions a researcher has to face when conducting an exploratory factor analysis. No common method for this purposes is always superior, so a new approach is proposed. The new approach combines an extensive data simulation with machine learning algorithms (complex statistical modeling). In a first step, data that reflect typical application contexts are created. Then in a second step, the machine learning modeling is used to find data characteristics that are able to predict the dimensionality (the number of factors). In a large-scale simulation study, this new approach was compared to four common methods varying the sample size, the number of variables per factor, the correlations between factors, loading magnitudes and the true number of factors. The new approach outperformed all four common approaches. Further, it was shown that the accuracy of the new approach could be increased by improving the machine learning model and the data basis. As the data basis can be easily extended for further application contexts, our new method promises better decision-making in exploratory factor analysis.
A meta-analysis was undertaken to reexamine near- and far-transfer effects following working-memory training and to consider potential moderators more systematically. Forty-seven studies with 65 ...group comparisons were included in the meta-analysis. Results showed near-transfer effects to short-term and working-memory skills that were sustained at follow-up with effect sizes ranging from g = 0.37 to g = 0.72 for immediate transfer and g = 0.22 to g = 0.78 for long-term transfer. Far-transfer effects to other cognitive skills were small, limited to nonverbal (g = 0.14) and verbal (g = 0.16) ability and not sustained at follow-up. Several moderators (e.g., duration of training sessions, supervision during training) had an influence on transfer effects, including far-transfer effects. We present principles for how best to improve working memory through training in the narrow-task paradigm and conjecture how best to improve basic cognitive functions in complex activity contexts.
Fit indices are widely used in order to test the model fit for structural equation models. In a highly influential study, Hu and Bentler (1999) showed that certain cutoff values for these indices ...could be derived, which, over time, has led to the reification of these suggested thresholds as "golden rules" for establishing the fit or other aspects of structural equation models. The current study shows how differences in unique variances influence the value of the global chi-square model test and the most commonly used fit indices: Root-mean-square error of approximation, standardized root-mean-square residual, and the comparative fit index. Using data simulation, the authors illustrate how the value of the chi-square test, the root-mean-square error of approximation, and the standardized root-mean-square residual are decreased when unique variances are increased although model misspecification is present. For a broader understanding of the phenomenon, the authors used different sample sizes, number of observed variables per factor, and types of misspecification. A theoretical explanation is provided, and implications for the application of structural equation modeling are discussed.
Exploratory factor analysis is a statistical method commonly used in psychological research to investigate latent variables and to develop questionnaires. Although such self-report questionnaires are ...prone to missing values, there is not much literature on this topic with regard to exploratory factor analysis—and especially the process of factor retention. Determining the correct number of factors is crucial for the analysis, yet little is known about how to deal with missingness in this process. Therefore, in a simulation study, six missing data methods (an expectation–maximization algorithm, predictive mean matching, Bayesian regression, random forest imputation, complete case analysis, and pairwise complete observations) were compared with respect to the accuracy of the parallel analysis chosen as retention criterion. Data were simulated for correlated and uncorrelated factor structures with two, four, or six factors; 12, 24, or 48 variables; 250, 500, or 1,000 observations and three different missing data mechanisms. Two different procedures combining multiply imputed data sets were tested. The results showed that no missing data method was always superior, yet random forest imputation performed best for the majority of conditions—in particular when parallel analysis was applied to the averaged correlation matrix rather than to each imputed data set separately. Complete case analysis and pairwise complete observations were often inferior to multiple imputation.
People with mental illness struggle with symptoms and with public stigma. Some accept common prejudices and lose self-esteem, resulting in shame and self-stigma, which may affect their interactions ...with mental health professionals. This study explored whether self-stigma and shame are associated with consumers' preferences for participation in medical decision making and their behavior in psychiatric consultations.
In a cross-sectional study conducted in Germany, 329 individuals with a diagnosis of a schizophrenia spectrum disorder or an affective disorder and their psychiatrists provided sociodemographic and illness-related information. Self-stigma, shame, locus of control, and views about clinical decision making were assessed by self-report. Psychiatrists rated their impression of the decision-making behavior of consumers. Regression analyses and structural equation modeling were used to determine the association of self-stigma and shame with clinical decision making.
Self-stigma was not related to consumers' participation preferences, but it was associated with some aspects of communicative behavior. Active and critical behavior (for example, expressing views, daring to challenge the doctor's opinion, and openly speaking out about disagreements with the doctor) was associated with less shame, less self-stigma, more self-responsibility, less attribution of external control to powerful others, and more years of education.
Self-stigma and shame were associated with less participative and critical behavior, which probably leads to clinical encounters that involve less shared decision making and more paternalistic decision making. Paternalistic decision making may reinforce self-stigma and lead to poorer health outcomes. Therefore, interventions that reduce self-stigma and increase consumers' critical and participative communication may improve health outcomes.
Transcranial direct current stimulation (tDCS) is a safe, effective treatment for major depressive disorder (MDD). While antidepressant effects are heterogeneous, no studies have investigated ...trajectories of tDCS response. We characterized distinct improvement trajectories and associated baseline characteristics for patients treated with prefrontal tDCS, an active pharmacotherapy (escitalopram), and placebo. This is a secondary analysis of a randomized, non-inferiority, double-blinded trial (ELECT-TDCS, N = 245). Participants were diagnosed with an acute unipolar, nonpsychotic, depressive episode, and presented Hamilton Depression Rating Scale (17-items, HAM-D) scores ≥17. Latent trajectory modeling was used to identify HAM-D response trajectories over a 10-week treatment. Top-down (hypothesis-driven) and bottom-up (data-driven) methods were employed to explore potential predictive features using, respectively, conservatively corrected regression models and a cross-validated stability ranking procedure combined with elastic net regularization. Three trajectory classes that were distinct in response speed and intensity (rapid, slow, and no/minimal improvement) were identified for escitalopram, tDCS, and placebo. Differences in response and remission rates were significant early for all groups. Depression severity, use of benzodiazepines, and age were associated with no/minimal improvement. No significant differences in trajectory assignment were found in tDCS vs. placebo comparisons (38.3, 34, and 27.6%; vs. 23.3, 43.3, and 33.3% for rapid, slow, and no/minimal trajectories, respectively). Additional features are suggested in bottom-up analyses. Summarily, groups treated with tDCS, escitalopram, and placebo differed in trajectory class distributions and baseline predictors of response. Our results might be relevant for designing further studies.
The COVID-19 pandemic is an inherently stressful situation, which may lead to adverse psychosocial outcomes in various populations. Yet, individuals may not be affected equally by stressors posed by ...the pandemic and those with pre-existing mental disorders could be particularly vulnerable. To test this hypothesis, we assessed the psychological response to the pandemic in a case–control design. We used an age-, sex- and employment status-matched case–control sample (
n
= 216) of psychiatric inpatients, recruited from the LMU Psychiatry Biobank Munich study and non-clinical individuals from the general population. Participants completed validated self-report measures on stress, anxiety, depression, paranoia, rumination, loneliness, well-being, resilience, and a newly developed index of stressors associated with the COVID-19 pandemic. Multiple linear regression analyses were conducted to assess the effects of group, COVID-19-specific stressors, and their interaction on the different psychosocial outcomes. While psychiatric inpatients reported larger mental health difficulties overall, the impact of COVID-19-specific stressors was lower in patients and not associated with worse psychological functioning compared to non-clinical individuals. In contrast, depressive symptoms, rumination, loneliness, and well-being were more strongly associated with COVID-19-specific stressors in non-clinical individuals and similar to the severity of inpatients for those who experienced the greatest COVID-19-specific stressor impact Contrary to expectations, the psychological response to the pandemic may not be worse in psychiatric inpatients compared to non-clinical individuals. Yet, individuals from the general population, who were hit hardest by the pandemic, should be monitored and may be in need of mental health prevention and treatment efforts.
Only two-thirds of patients admitted to psychiatric wards return to their previous jobs. Return-to-work interventions in Germany are investigated for their effectiveness, but information regarding ...cost-effectiveness is lacking. This study investigates the cost-utility of a return-to-work intervention for patients with mental disorders compared to treatment as usual (TAU).
We used data from a cluster-randomised controlled trial including 166 patients from 28 inpatient psychiatric wards providing data at 6- and 12-month follow-ups. Health and social care service use was measured with the Client Sociodemographic and Service Receipt Inventory. Quality of life was measured with the EQ-5D-3L questionnaire. Cost-utility analysis was performed by calculating additional costs per one additional QALY (Quality-Adjusted Life Years) gained by receiving the support of return-to-work experts, in comparison to TAU.
No significant cost or QALY difference between the intervention and control groups has been detected. The return-to-work intervention cannot be identified as cost-effective in comparison to TAU.
The employment of return-to-work experts could not reach the threshold of providing good value for money. TAU, therefore, seems to be sufficient support for the target group.
Diagnostic reasoning in primary care setting where presented problems and patients are mostly unselected appears as a complex process. The aim was to develop a questionnaire to describe how general ...practitioners (GPs) deal with uncertainty to gain more insight into the decisional process. The association of personality traits with medical decision making was investigated additionally.
Raw items were identified by literature research and focus group. Items were improved by interviewing ten GPs with thinking-aloud-method. A personal case vignette related to a complex and uncertainty situation was introduced. The final questionnaire was administered to 228 GPs in Germany. Factorial validity was calculated with explorative and confirmatory factor analysis. The results of the Communicating and Dealing with Uncertainty (CoDU)-questionnaire were compared with the scales of the 'Physician Reaction to Uncertainty' (PRU) questionnaire and with the personality traits which were determined with the Big Five Inventory (BFI-K).
The items could be assigned to four scales with varying internal consistency, namely 'communicating uncertainty' (Cronbach alpha 0.79), 'diagnostic action' (0.60), 'intuition' (0.39) and 'extended social anamnesis' (0.69). Neuroticism was positively associated with all PRU scales 'anxiety due to uncertainty' (Pearson correlation 0.487), 'concerns about bad outcomes' (0.488), 'reluctance to disclose uncertainty to patients' (0.287), 'reluctance to disclose mistakes to physicians' (0.212) and negatively associated with the CoDU scale 'communicating uncertainty' (-0.242) (p<0.01 for all). 'Extraversion' (0.146; p<0.05), 'agreeableness' (0.145, p<0.05), 'conscientiousness' (0.168, p<0.05) and 'openness to experience' (0.186, p<0.01) were significantly positively associated with 'communicating uncertainty'. 'Extraversion' (0.162), 'consciousness' (0.158) and 'openness to experience' (0.155) were associated with 'extended social anamnesis' (p<0.05).
The questionnaire allowed describing the diagnostic decision making process of general practitioners in complex situations. Personality traits are associated with diagnostic reasoning and communication with patients, which might be important for medical education and quality improvement purposes.