The revision and factor analytic evaluation of the German version of the depression literacy scale (D-Lit-R German).

BACKGROUND: Depression is a common mental health disorder and the second leading cause of disability worldwide. In people with depression, low depression literacy, which could be characterized by a poor recognition of depressive symptoms and less knowledge about the availability of treatment options, can hinder adequate therapy for depression. Nevertheless, questionnaires measuring depression literacy in Germany are rare. Consequently, for the present study, the German Depression Literacy Scale (D-Lit) has been revised and evaluated. METHODS: First, a team of clinical psychologists revised the D-Lit German scale. Next, cognitive interviews were conducted with patients with depression to improve the comprehensibility of the scale items. Our revision of the D-Lit-R German scale was then subjected to an anonymous online study. Finally, the data went through an exploratory factor analysis, and sociodemographic subgroup analyses were performed. RESULTS: N = 524 individuals (age 18-80) completed the D-Lit-R German scale and a questionnaire on their sociodemographic data. Cronbach´s alpha was estimated as α = .72, and McDonald's Omega (categorical) was estimated as ω = .77. The mean Item difficulty was M = .75 (SD = .15). An EFA was performed for a unidimensional model, a 5-factor-model and at last a 3-factor-model. The 5-factorial model showed a good model fit (χ2emp,WLSMV(131) = 92.424, p > .05; CFI = 1, RMSEA = 0, SRMR = .07) but was rejected since the content of the potential 5 factors could not be determined. The 3-factor model showed an arguable model fit. The Chi2 test was significant (χ2emp,WLSMV(168) = 199.912, p < .05), but the CFI and the RMSEA met an acceptable model fit (CFI = .990, RMSEA of .019, 90% CI[.003, .029]). Substantively, the three factors were defined as (1) Distractors and other symptoms, (2) Depressive symptoms, and (3) Pharmacological and psychotherapeutic depression treatment. Furthermore, there were significant differences in sum scores regarding the subgroup's gender, treatment for mental health problems, depression treatment, experience with depression, and different career fields. CONCLUSIONS: The D-Lit-R German scale is a time-efficient scale to assess some aspects of the depression literacy construct that can be easily applied. Since there was no perfect model fit, it is recommended to continue to revise the scale. Further evaluation studies could ask for knowledge of the etiological factors of depression. Future studies could then use this instrument to convey depression literacy. This instrument could assess the growth of knowledge after psychoeducational interventions in different settings. TRIAL REGISTRATION: This trial was preregistered at the platform osf.io ( https://osf.io/49xdh ). REGISTRATION NUMBER: https://doi.org/10.17605/OSF.IO/49XDH Date of registration: 28 April 2022.

Evaluating Model Fit of Measurement Models in Confirmatory Factor Analysis.

Confirmatory factor analyses (CFA) are often used in psychological research when developing measurement models for psychological constructs. Evaluating CFA model fit can be quite challenging, as tests for exact model fit may focus on negligible deviances, while fit indices cannot be interpreted absolutely without specifying thresholds or cutoffs. In this study, we review how model fit in CFA is evaluated in psychological research using fit indices and compare the reported values with established cutoff rules. For this, we collected data on all CFA models in Psychological Assessment from the years 2015 to 2020 (NStudies=221). In addition, we reevaluate model fit with newly developed methods that derive fit index cutoffs that are tailored to the respective measurement model and the data characteristics at hand. The results of our review indicate that the model fit in many studies has to be seen critically, especially with regard to the usually imposed independent clusters constraints. In addition, many studies do not fully report all results that are necessary to re-evaluate model fit. We discuss these findings against new developments in model fit evaluation and methods for specification search.

Everything has its price: Foundations of cost-sensitive machine learning and its application in psychology.

Psychology has seen an increase in the use of machine learning (ML) methods. In many applications, observations are classified into one of two groups (binary classification). Off-the-shelf classification algorithms assume that the costs of a misclassification (false positive or false negative) are equal. Because this is often not reasonable (e.g., in clinical psychology), cost-sensitive machine learning (CSL) methods can take different cost ratios into account. We present the mathematical foundations and introduce a taxonomy of the most commonly used CSL methods, before demonstrating their application and usefulness on psychological data, that is, the drug consumption data set (N = 1, 885) from the University of California Irvine ML Repository. In our example, all demonstrated CSL methods noticeably reduced mean misclassification costs compared to regular ML algorithms. We discuss the necessity for researchers to perform small benchmarks of CSL methods for their own practical application. Thus, our open materials provide R code, demonstrating how CSL methods can be applied within the mlr3 framework (https://osf.io/cvks7/). (PsycInfo Database Record (c) 2023 APA, all rights reserved).