Florian Scharf

Although machine learning (ML) methods are gaining popularity in psychological research, the debate about their usefulness ranges from hype to disillusionment. The discrepancy between the hopes placed in ML methods and the empirical reality is often attributed to the quality of psychological data sets, which tend to be small and subject to imprecise measurement. In this simulation study, we examined the data requirements necessary for ML methods to perform well. We compared the performance of elastic net regressions with and without prespecified interactions, random forests, and gradient boosting machines for different data-generating processes (including interaction, stepwise, or piecewise linear effects) and under various conditions: (a) sample size, (b) number of irrelevant predictors, (c) predictor reliability, (d) effect size, and (e) nature of the data-generating process (i.e., linear vs. nonlinear effects). We investigated whether the models achieved the highest level of predictive performance attainable under the given simulated conditions. There were two main takeaways from our results: First, the maximum possible predictive performance was only achieved under optimal simulation conditions (N = 1,000, perfectly reliable predictors, predominantly linear effects, and an exceptionally large effect size of R² = .80), which are arguably rarely met in psychological research. Second, each ML model outperformed the others under certain conditions, but none was consistently superior or entirely robust to suboptimal data characteristics. We stress that data quality fundamentally limits predictive performance and discuss the interpretation of comparisons between flexible ML models and simpler (regularized linear) baselines in psychological research. (PsycInfo Database Record (c) 2026 APA, all rights reserved).

Metaheuristics are increasingly used in the construction of psychological measures, particularly for developing short scales (e.g., Achaa-Amankwaa et al., 2025; Jing et al., 2022; Raborn et al., 20...

Background: The exponential growth of telehealth is revolutionizing health care delivery, but its evaluation has not matched the pace of its uptake. Various forms of assessment, from single-item to more extensive questionnaires, have been used to assess telehealth and digital therapeutics and their usability. The most frequently used questionnaire is the “Telehealth Usability Questionnaire” (TUQ). The use of the TUQ is limited by its restricted availability in languages other than English and its feasibility. Objective: The aims of this study were to create a translated German TUQ version and to derive a short questionnaire for patients—“Telehealth Usability and Perceived Usefulness Short Questionnaire for patients” (TUUSQ). Methods: As a first step, the original 21-item TUQ was forward and back-translated twice. In the second step, 13 TUQ items were selected for their suitability for the general evaluation of telehealth on the basis of expert opinion. These 13 items were surveyed between July 2022 and September 2023 in 4 studies with patients and family members of palliative care, as well as patients with chronic autoimmune diseases, evaluating 13 health care apps, including digital therapeutics and a telehealth system (n1=128, n2=220, n3=30, and n4=12). Psychometric exploratory factor analysis was conducted. Results: The analysis revealed that a parsimonious factor structure with 2 factors (“perceived usefulness in health care” and “usability”) is sufficient to describe the patient’s perception. Consequently, the questionnaire could be shortened to 6 items without compromising its informativeness. Conclusions: We provide a linguistically precise German version of the TUQ for assessing the usability and perceived usefulness of telehealth. Beyond that, we supply a highly feasible shortened version that is versatile for general use in telehealth, mobile health, and digital therapeutics, which distinguishes between the 2 factors “perceived usefulness in health care” and “usability” in patients. Trial Registration: German Clinical Trials Register DRKS00030546; https://drks.de/search/de/trial/DRKS00030546

BACKGROUND The exponential growth of telehealth is revolutionizing health care delivery, but its evaluation has not matched the pace of its uptake. Various forms of assessment, from single-item to more extensive questionnaires, have been used to assess telehealth and digital therapeutics and their usability. The most frequently used questionnaire is the “Telehealth Usability Questionnaire” (TUQ). The use of the TUQ is limited by its restricted availability in languages other than English and its feasibility. OBJECTIVE The aims of this study were to create a translated German TUQ version and to derive a short questionnaire for patients—“Telehealth Usability and Perceived Usefulness Short Questionnaire for patients” (TUUSQ). METHODS As a first step, the original 21-item TUQ was forward and back-translated twice. In the second step, 13 TUQ items were selected for their suitability for the general evaluation of telehealth on the basis of expert opinion. These 13 items were surveyed between July 2022 and September 2023 in 4 studies with patients and family members of palliative care, as well as patients with chronic autoimmune diseases, evaluating 13 health care apps, including digital therapeutics and a telehealth system (n1=128, n2=220, n3=30, and n4=12). Psychometric exploratory factor analysis was conducted. RESULTS The analysis revealed that a parsimonious factor structure with 2 factors (“perceived usefulness in health care” and “usability”) is sufficient to describe the patient’s perception. Consequently, the questionnaire could be shortened to 6 items without compromising its informativeness. CONCLUSIONS We provide a linguistically precise German version of the TUQ for assessing the usability and perceived usefulness of telehealth. Beyond that, we supply a highly feasible shortened version that is versatile for general use in telehealth, mobile health, and digital therapeutics, which distinguishes between the 2 factors “perceived usefulness in health care” and “usability” in patients. CLINICALTRIAL German Clinical Trials Register DRKS00030546; https://drks.de/search/de/trial/DRKS00030546

The ability to shield against distraction while focusing on a task requires the operation of executive functions and is essential for successful learning. We investigated the short‐term dynamics of distraction control in a data set of 269 children aged 4–10 years and 51 adults pooled from three studies using multilevel models. Participants performed a visual categorization task while a task‐irrelevant sequence of sounds was presented which consisted of frequently repeated standard sounds and rarely interspersed novel sounds. On average, participants responded slower in the categorization task after novel sounds. This distraction effect was more pronounced in children. Throughout the experiment, the initially strong distraction effects declined to the level of adults in the groups of 6‐ to 10‐year‐olds. Such a decline was neither observed in the groups of the 4‐ and 5‐year‐olds, who consistently showed a high level of distraction, nor in adults, who showed a constantly low level of distraction throughout the experimental session. Results indicate that distraction control is a highly dynamic process that qualitatively and quantitatively differs between age groups. We conclude that the analysis of short‐term dynamics provides valuable insights into the development of attention control and might explain inconsistent findings regarding distraction control in middle childhood. In addition, models of attention control need to be refined to account for age‐dependent rapid learning mechanisms. Our findings have implications for the design of learning situations and provide an additional source of information for the diagnosis and treatment of children with attention deficit disorders.

Multicollinearity between predictors is a common concern in SEM applications. As in linear regression models, high correlations between predictors can lead to unstable parameter estimates (i.e., large standard errors) and reduced statistical power. Regularized estimation methods, which have recently become available for SEMs, may provide more stable estimates in the presence of multicollinearity at the cost of a certain amount of bias in the estimated parameters. In a simulation study, we compared the performance of nonregularized SEM with Ridge and Elastic net regularized SEMs in the presence of strong multicollinearity. The results provide evidence that Ridge and Elastic net regularized SEMs provide more stable estimates and greater statistical power than nonregularized SEM. However, the biases from regularized estimation can result in increased Type I error rates. This phenomenon was more pronounced in Ridge than in Elastic net regularized SEMs. We discuss when the benefits can outweigh this cost.

New task-irrelevant sounds can distract attention. This study specifies the impact of stimulus novelty and of learning on attention control in three groups of children aged 6–7, 8, and 9–10 years and an adult control group. Participants (N = 179) were instructed to ignore a sound sequence including standard sounds and novel or repeated distractor sounds, while performing a visual categorization task. Distractor sounds impaired performance in children more than in adult controls, demonstrating the long-term development of attention control. Children, but not adults, were more distracted by novel than by repeated sounds, indicating increased sensitivity to novel information. Children, in particular younger children, were highly distracted during the first presentations of novel sounds compared to adults, while no age differences were observed for the last presentations. Results highlight the age-related impact of auditory novel information on attention and characterize the rapid development of attention control mechanisms as a function of age and exposure to irrelevant novel sounds.

It is challenging to apply exploratory factor analysis (EFA) to event-related potential (ERP) data because such data are characterized by substantial temporal overlap (i.e., large cross-loadings) between the factors, and, because researchers are typically interested in the results of subsequent analyses (e.g., experimental condition effects on the level of the factor scores). In this context, relatively small deviations in the estimated factor solution from the unknown ground truth may result in substantially biased estimates of condition effects (rotation bias). Thus, in order to apply EFA to ERP data researchers need rotation methods that are able to both recover perfect simple structure where it exists and to tolerate substantial cross-loadings between the factors where appropriate. We had two aims in the present paper. First, to extend previous research, we wanted to better understand the behavior of the rotation bias for typical ERP data. To this end, we compared the performance of a variety of factor rotation methods under conditions of varying amounts of temporal overlap between the factors. Second, we wanted to investigate whether the recently proposed component loss rotation is better able to decrease the bias than traditional simple structure rotation. The results showed that no single rotation method was generally superior across all conditions. Component loss rotation showed the best all-round performance across the investigated conditions. We conclude that Component loss rotation is a suitable alternative to simple structure rotation. We discuss this result in the light of recently proposed sparse factor analysis approaches.

Exploratory factor analysis (EFA) is an important tool when the measurement structure of psychological constructs is uncertain. Typically, factor rotation is applied to obtain interpretable results resembling a simple structure. However, an overwhelming multitude of rotation techniques is available of which none is unequivocally superior. Recently, regularization has been suggested as an alternative to factor rotation. In two simulation studies, we addressed the question if regularized EFA is a suitable alternative for rotated EFA. We compared their performance in recovering predefined factor loading patterns with varying amounts of cross-loadings. Elastic net regularized EFA yielded estimates comparable to rotated EFA. For complex loading patterns, both rotated and regularized EFA tended to underestimate cross-loadings and inflate factor correlations, but regularized EFA was able to recover loading patterns as long as a subset of items followed a simple structure. We conclude that regularization is a suitable alternative to factor rotation for psychometric applications.