Exploring Estimation Procedures for Reducing Dimensionality in Psychological Network Modeling.

To understand psychological data, it is crucial to examine the structure and dimensions of variables. In this study, we examined alternative estimation algorithms to the conventional GLASSO-based exploratory graph analysis (EGA) in network psychometric models to assess the dimensionality structure of the data. The study applied Bayesian conjugate or Jeffreys' priors to estimate the graphical structure and then used the Louvain community detection algorithm to partition and identify groups of nodes, which allowed the detection of the multi- and unidimensional factor structures. Monte Carlo simulations suggested that the two alternative Bayesian estimation algorithms had comparable or better performance when compared with the GLASSO-based EGA and conventional parallel analysis (PA). When estimating the multidimensional factor structure, the analytically based method (i.e., EGA.analytical) showed the best balance between accuracy and mean biased/absolute errors, with the highest accuracy tied with EGA but with the smallest errors. The sampling-based approach (EGA.sampling) yielded higher accuracy and smaller errors than PA; lower accuracy but also lower errors than EGA. Techniques from the two algorithms had more stable performance than EGA and PA across different data conditions. When estimating the unidimensional structure, the PA technique performed the best, followed closely by EGA, and then EGA.analytical and EGA.sampling. Furthermore, the study explored four full Bayesian techniques to assess dimensionality in network psychometrics. The results demonstrated superior performance when using Bayesian hypothesis testing or deriving posterior samples of graph structures under small sample sizes. The study recommends using the EGA.analytical technique as an alternative tool for assessing dimensionality and advocates for the usefulness of the EGA.sampling method as a valuable alternate technique. The findings also indicated encouraging results for extending the regularization-based network modeling EGA method to the Bayesian framework and discussed future directions in this line of work. The study illustrated the practical application of the techniques to two empirical examples in R.

Investigating Best Practices for Ecological Momentary Assessment: Nationwide Factorial Experiment.

BACKGROUND: Ecological momentary assessment (EMA) is a measurement methodology that involves the repeated collection of real-time data on participants' behavior and experience in their natural environment. While EMA allows researchers to gain valuable insights into dynamic behavioral processes, the need for frequent self-reporting can be burdensome and disruptive. Compliance with EMA protocols is important for accurate, unbiased sampling; yet, there is no "gold standard" for EMA study design to promote compliance. OBJECTIVE: The purpose of this study was to use a factorial design to identify optimal study design factors, or combinations of factors, for achieving the highest completion rates for smartphone-based EMAs. METHODS: Participants recruited from across the United States were randomized to 1 of 2 levels on each of 5 design factors in a 2×2×2×2×2 design (32 conditions): factor 1-number of questions per EMA survey (15 vs 25); factor 2-number of EMAs per day (2 vs 4); factor 3-EMA prompting schedule (random vs fixed times); factor 4-payment type (US $1 paid per EMA vs payment based on the percentage of EMAs completed); and factor 5-EMA response scale type (ie, slider-type response scale vs Likert-type response scale; this is the only within-person factor; each participant was randomized to complete slider- or Likert-type questions for the first 14 days or second 14 days of the study period). All participants were asked to complete prompted EMAs for 28 days. The effect of each factor on EMA completion was examined, as well as the effects of factor interactions on EMA completion. Finally, relations between demographic and socioenvironmental factors and EMA completion were examined. RESULTS: Participants (N=411) were aged 48.4 (SD 12.1) years; 75.7% (311/411) were female, 72.5% (298/411) were White, 18.0% (74/411) were Black or African American, 2.7% (11/411) were Asian, 1.5% (6/411) were American Indian or Alaska Native, 5.4% (22/411) belonged to more than one race, and 9.6% (38/396) were Hispanic/Latino. On average, participants completed 83.8% (28,948/34,552) of scheduled EMAs, and 96.6% (397/411) of participants completed the follow-up survey. Results indicated that there were no significant main effects of the design factors on compliance and no significant interactions. Analyses also indicated that older adults, those without a history of substance use problems, and those without current depression tended to complete more EMAs than their counterparts. No other demographic or socioenvironmental factors were related to EMA completion rates. Finally, the app was well liked (ie, system usability scale score=82.7), and there was a statistically significant positive association between liking the app and EMA compliance. CONCLUSIONS: Study results have broad implications for developing best practices guidelines for future studies that use EMA methodologies. TRIAL REGISTRATION: ClinicalTrials.gov number NCT05194228; https://clinicaltrials.gov/study/NCT05194228.

Customizing Bayesian multivariate generalizability theory to mixed-format tests.

Mixed-format tests, which typically include dichotomous items and polytomously scored tasks, are employed to assess a wider range of knowledge and skills. Recent behavioral and educational studies have highlighted their practical importance and methodological developments, particularly within the context of multivariate generalizability theory. However, the diverse response types and complex designs of these tests pose significant analytical challenges when modeling data simultaneously. Current methods often struggle to yield reliable results, either due to the inappropriate treatment of different types of response data separately or the imposition of identical covariates across various response types. Moreover, there are few software packages or programs that offer customized solutions for modeling mixed-format tests, addressing these limitations. This tutorial provides a detailed example of using a Bayesian approach to model data collected from a mixed-format test, comprising multiple-choice questions and free-response tasks. The modeling was conducted using the Stan software within the R programming system, with Stan codes tailored to the structure of the test design, following the principles of multivariate generalizability theory. By further examining the effects of prior distributions in this example, this study demonstrates how the adaptability of Bayesian models to diverse test formats, coupled with their potential for nuanced analysis, can significantly advance the field of psychometric modeling.

Top-Down Proteomics Analysis of Picogram-Level Complex Samples Using Spray-Capillary-Based Capillary Electrophoresis-Mass Spectrometry.

Proteomics analysis of mass-limited samples has become increasingly important for understanding biological systems in physiologically relevant contexts such as patient samples, multicellular organoids, spheroids, and single cells. However, relatively low sensitivity in top-down proteomics methods makes their application to mass-limited samples challenging. Capillary electrophoresis (CE) has emerged as an ideal separation method for mass-limited samples due to its high separation resolution, ultralow detection limit, and minimal sample volume requirements. Recently, we developed "spray-capillary", an electrospray ionization (ESI)-assisted device, that is capable of quantitative ultralow-volume sampling (e.g., pL-nL level). Here, we developed a spray-capillary-CE-MS platform for ultrasensitive top-down proteomics analysis of intact proteins in mass-limited complex biological samples. Specifically, to improve the sensitivity of the spray-capillary platform, we incorporated a polyethylenimine (PEI)-coated capillary and optimized the spray-capillary inner diameter. Under optimized conditions, we successfully detected over 200 proteoforms from 50 pg of E. coli lysate. To our knowledge, the spray-capillary CE-MS platform developed here represents one of the most sensitive detection methods for top-down proteomics. Furthermore, in a proof-of-principle experiment, we detected 261 ± 65 and 174 ± 45 intact proteoforms from fewer than 50 HeLa and OVCAR-8 cells, respectively, by coupling nanodroplet-based sample preparation with our optimized CE-MS platform. Overall, our results demonstrate the capability of the modified spray-capillary CE-MS platform to perform top-down proteomics analysis on picogram amounts of samples. This advancement presents the possibility of meaningful top-down proteomics analysis of mass-limited samples down to the level of single mammalian cells.

Longitudinal association between subjective and objective memory in older adults: a study with the Virginia Cognitive Aging Project sample.

Using the bivariate dual change score approach, the present study investigated the directionality of the SMC-OMP association in a sample of healthy older adults (N = 2,057) from the Virginia Cognitive Aging Project. The sample was assessed throughout 10 years, five time points, and the impact of education, depressive symptoms, and low-memory functioning was tested. The Memory Functioning Questionnaire was used to assess SMC. There was a lack of longitudinal association with no significant coupling effects found between subjective and objective memory. After including depressive symptoms as a covariate, Frequency of Forgetting significantly predicted subsequent negative changes in OMP . A similar result was found for the low-memory functioning group after the inclusion of depression, with the frequency of memory complaints predicting subsequent memory decline . Our results do not support a predictive value of SMC without accounting for the influence of depressive symptoms and low-memory functioning.

Depressive symptoms as a predictor of memory decline in older adults: A longitudinal study using the dual change score model.

The directionality of the longitudinal association between depressive symptoms and memory remains a topic of intense debate. A unidirectional association where depression impacts the change in memory (or vice-versa) and a bidirectional association where the trajectories of both dimensions affect each other lead to different clinical implications. METHOD: This study investigated the depression-memory longitudinal association in a sample of 2057 older adults aged between 60 and 99 years old from the Virginia Cognitive Aging Project. The bivariate dual change score model was used to investigate the directionality of the association between episodic memory and three dimensions of depression (somatic symptoms, depressed affect, and positive affect) throughout ten years (five measurement points), controlling for education and sex. RESULTS: the bidirectional model showed the best fit between somatic symptoms and memory, with a significant coupling effect observed from initial somatic symptoms to subsequent changes in memory. For depressed and positive affect, the unidirectional model with initial levels of depression predicting following changes in memory showed the best fit to the data, with significant coupling effects observed. Higher initial levels of somatic symptoms and depressed affect predicted a subsequent decline in memory, and higher initial levels of positive affect predicted subsequent better memory performance. Statistical adjustments for covariates (education and sex) had no significant influence on these associations. CONCLUSIONS: Our findings support a unidirectional association with higher depressive symptoms preceding a steeper decline in memory in older adults. We discuss the clinical implications for depressive symptoms as a predictor of subsequent memory decline.

Entropy Fit Indices: New Fit Measures for Assessing the Structure and Dimensionality of Multiple Latent Variables.

The accurate identification of the content and number of latent factors underlying multivariate data is an important endeavor in many areas of Psychology and related fields. Recently, a new dimensionality assessment technique based on network psychometrics was proposed (Exploratory Graph Analysis, EGA), but a measure to check the fit of the dimensionality structure to the data estimated via EGA is still lacking. Although traditional factor-analytic fit measures are widespread, recent research has identified limitations for their effectiveness in categorical variables. Here, we propose three new fit measures (termed entropy fit indices) that combines information theory, quantum information theory and structural analysis: Entropy Fit Index (EFI), EFI with Von Neumman Entropy (EFI.vn) and Total EFI.vn (TEFI.vn). The first can be estimated in complete datasets using Shannon entropy, while EFI.vn and TEFI.vn can be estimated in correlation matrices using quantum information metrics. We show, through several simulations, that TEFI.vn, EFI.vn and EFI are as accurate or more accurate than traditional fit measures when identifying the number of simulated latent factors. However, in conditions where more factors are extracted than the number of factors simulated, only TEFI.vn presents a very high accuracy. In addition, we provide an applied example that demonstrates how the new fit measures can be used with a real-world dataset, using exploratory graph analysis.

Corrigendum: A Bayesian Approach to the Analysis of Local Average Treatment Effect for Missing and Non-normal Data in Causal Modeling: A Tutorial With the ALMOND Package in R.

[This corrects the article DOI: 10.3389/fpsyg.2020.00169.].

A Bayesian Approach to the Analysis of Local Average Treatment Effect for Missing and Non-normal Data in Causal Modeling: A Tutorial With the ALMOND Package in R.

One practical challenge in observational studies and quasi-experimental designs is selection bias. The issue of selection bias becomes more concerning when data are non-normal and contain missing values. Recently, a Bayesian robust two-stage causal modeling with instrumental variables was developed and has the advantages of addressing selection bias and handle non-normal data and missing data simultaneously in one model. The method provides reliable parameter and standard error estimates when missing data and outliers exist. The modeling technique can be widely applied to empirical studies particularly in social, psychological and behavioral areas where any of the three issues (e.g., selection bias, data with outliers and missing data) is commonly seen. To implement this method, we developed an R package named ALMOND (Analysis of LATE (Local Average Treatment Effect) for Missing Or/and Nonnormal Data). Package users have the flexibility to directly apply the Bayesian robust two-stage causal models or write their own Bayesian models from scratch within the package. To facilitate the application of the Bayesian robust two-stage causal modeling technique, we provide a tutorial for the ALMOND package in this article, and illustrate the application with two examples from empirical research.

Investigating the performance of exploratory graph analysis and traditional techniques to identify the number of latent factors: A simulation and tutorial.

Exploratory graph analysis (EGA) is a new technique that was recently proposed within the framework of network psychometrics to estimate the number of factors underlying multivariate data. Unlike other methods, EGA produces a visual guide-network plot-that not only indicates the number of dimensions to retain, but also which items cluster together and their level of association. Although previous studies have found EGA to be superior to traditional methods, they are limited in the conditions considered. These issues are addressed through an extensive simulation study that incorporates a wide range of plausible structures that may be found in practice, including continuous and dichotomous data, and unidimensional and multidimensional structures. Additionally, two new EGA techniques are presented: one that extends EGA to also deal with unidimensional structures, and the other based on the triangulated maximally filtered graph approach (EGAtmfg). Both EGA techniques are compared with 5 widely used factor analytic techniques. Overall, EGA and EGAtmfg are found to perform as well as the most accurate traditional method, parallel analysis, and to produce the best large-sample properties of all the methods evaluated. To facilitate the use and application of EGA, we present a straightforward R tutorial on how to apply and interpret EGA, using scores from a well-known psychological instrument: the Marlowe-Crowne Social Desirability Scale. (PsycInfo Database Record (c) 2020 APA, all rights reserved).

Longitudinal Model Building Using Latent Transition Analysis: An Example Using School Bullying Data.

Applications of latent transition analysis (LTA) have emerged since the early 1990s, with numerous scientific findings being published in many areas, including social and behavioral sciences, education, and public health. Although LTA is effective as a statistical analytic tool for a person-centered model using longitudinal data, model building in LTA has often been subjective and confusing for applied researchers. To fill this gap in the literature, we review the components of LTA, recommend a framework of fitting LTA, and summarize what acceptable model evaluation tools should be used in practice. The proposed framework of fitting LTA consists of six steps depicted in Figure 1 from step 0 (exploring data) to step 5 (fitting distal variables). We also illustrate the framework of fitting LTA with data on concerns about school bullying from a sample of 1,180 students ranging from 5th to 9th grade (mean age = 12.2 years, SD = 1.29 years at Time 1) over three semesters. We identified four groups of students with distinct patterns of bullying concerns, and found that their concerns about bullying decreased and narrowed to specific concerns about rumors, gossip, and social exclusion over time. The data and command (syntax) files needed for reproducing the results using SAS PROC LCA and PROC LTA (Version 1.3.2) (2015) and Mplus 7.4 (Muthén and Muthén, 1998-2015) are provided as online supplementary materials.