Bayesian Structural Equation Modeling (BSEM) has gained significant attention due to its ability to resolve common issues found in frequentist approaches, such as nonconvergence, Heywood cases, sample size limitations, and inadmissible solutions. Furthermore, BSEM can estimate complex models that classical maximum likelihood methods often struggle with. A crucial component of BSEM is the incorporation of prior knowledge via prior distributions, which provides a unique advantage over frequentist methods by allowing previously known information to be transparently included in model specifications. Proper prior elicitation is essential for translating domain expertise into probability distributions, thus improving the accuracy and reliability of the model. Despite this, the development and widespread adoption of robust prior elicitation techniques in BSEM remain limited. This project aims to advance the field of BSEM through innovative computational methods and practical applications, with a focus on GPU processing and its potential to enhance the efficiency of Bayesian computations. By leveraging parallel computing capabilities provided by modern graphic processing units, the project seeks to significantly accelerate the computational processes involved in BSEM. Additionally, the project will explore the use of BSEM in developing psychometric instruments, employing techniques such as Markov Chain Monte Carlo (MCMC) using the No-U-Turn Sampler (NUTS) for latent model estimation. These innovations promise to offer deeper insights into measurement precision and enhance the validity of psychometric instruments across diverse populations. The expected outcomes of this project include improved computational efficiency, optimized model estimations, and broader adoption of Bayesian methods in applied research settings. By addressing both theoretical and practical challenges, this project aims to contribute to the broader use of BSEM in psychometric analysis.

Bayesian structural equation modeling (BSEM) is receiving increasing interest primarily due to its ability to address some of the issues found in the mainstream frequentist approach (e.g., nonconvergence, Heywood cases, sample size limitations, and inadmissible solutions). Additionally, BSEM allows for the fitting of complex models that classical maximum likelihood methods might struggle to handle. A critical component of any Bayesian analysis is the prior distribution of the unknown model parameters. A key distinction between Bayesian structural equation modeling and frequentist structural equation modeling is the use of priors. Researchers may be skeptical about the subjectivity of prior distributions and their impact on Bayesian modeling. However, priors are a significant advantage of using Bayesian statistics, as they allow previously known information to be transparently and directly included in the model specification. Proper prior elicitation is essential for translating knowledge and judgment about a phenomenon into a probability distribution. Priors allow for the quantification of uncertainty and encapsulate available knowledge about the parameters before observing the data. There are several ways to translate prior knowledge into distribution parameters. Results show that researchers tend to rely on weakly informative priors (i.e., small-variance priors). However, prior elicitation in Bayesian structural equation modeling still has a long way to go in terms of development and widespread adoption.

Traditional psychometric approaches often rely on frequentist models, which can be limited in handling uncertainty and incorporating prior knowledge. By adopting a Bayesian framework, this project aims to enhance psychometric analysis through more flexible, probabilistic modeling techniques that allow for dynamic updates as new data becomes available. The project focuses on the creation and adaptation of psychometric instruments for diverse populations. Advanced computational techniques, including Markov Chain Monte Carlo (MCMC) using the No-U-Turn Sampler (NUTS), are employed for latent model estimation. The Bayesian approach provides a deeper understanding of measurement precision and contributes to the development of psychometric instruments with strong validity evidence.

Bayesian structural equation modeling (BSEM) is receiving increasing interest mainly due to its capability of solving some of the issues found in the mainstream frequentist approach (e.g., nonconvergence, Heywood cases, sample size, inadmissible solutions) and because it allows fitting complex models that classical maximum likelihood methods might struggle to fit (Merkle & Rosseel, 2018). However, BSEM can be computationally intensive. In fact, the computational cost of the Bayesian analysis harmed the more frequent use of Bayesian statistics. The use of Bayesian methods has improved, mainly due to the computational advances, presenting researchers with more flexible, and powerful tools. Nowadays, Bayesian analysis is an established branch of methodology for model estimation (van de Schoot et al., 2021). In part, this is due to two aspects: the increased popularity of Bayesian methodology, and the advent of Markov chain Monte Carlo (MCMC) methods (Depaoli, 2021). Bayesian statistics benefit from MCMC methods since Bayesian analysis heavily relies on multidimensional integration. MCMC comprises a set of computational algorithms that can help to solve high‐dimensional, and complex modeling situations (South et al., 2022). MCMC can help Bayesian statistics by — for example — reconstructing the posterior distribution (Depaoli, 2021). MCMC can benefit greatly from a parallel computing environment, which allows to perform extensive calculations simultaneously. The advances in consumer computer hardware make parallel computing widely available to most users. Many computer video graphic cards support parallel computing. The use of the graphics processing units (GPU) usually provide meaningful gains in terms of performance (Češnovar et al., 2019). There is no doubt that parallel computing is of deep importance, the use of this technology can greatly improve several fields of statistics. One of those fields is BSEM, as so, the objective of this project is to understand th...

Since its origins to the relative explosion of team research in applied psychology and organizational behavior, several advances in the methods used to study team dynamics appeared (Mathieu et al., 2018). A paradigm capable of capturing the complex, dynamic nature of teamwork new research paradigm is required to move forward our understanding (Mathieu et al., 2008). Since individuals work in teams, the social dynamics are at play, creating emergent properties that interrelate with team processes impacting on team performance (Waller et al., 2016). One data point or simple measurement is not enough to capture such a complex process (Humphrey & Aime, 2014). Complex processes demand complex research methods (Boist & McKelvey, 2011). Team research cannot continue to disregard such complexities, risking its growth and future advancements. Validity assessment of team-level instruments is mostly performed using procedures designed for individual-level measures. However, the study of team-level instruments should include the possible inequality in the within- and between-level structure and should also consider information about scale item’s ability to differentiate groups (Bliese et al., 2019). We based our application in the most recent proposals related to multilevel theory, measurement, and validation. The first goal is to validate multilevel constructs, i.e., constructs that emerge from the interactions between individuals but that exist at both levels (individual and team). The second goal concerns the assessment and validation of emergent team constructs, which can be different in their nature (Mathieu & Luciano, 2019) and also in their measurement (Jebb et al., 2019). The last goal is to evaluate the longitudinal validity of dynamic team constructs (Luciano et al., 2018). This proposal clear contributes to advance team-level construct validation by integrating different approaches, implemented with top international collaboration and using advanced stati...

O PROJETO DTE vai disponibilizar um conjunto de funcionalidades inovadoras, que recorrerá a tecnologias nas áreas de inteligência artificial e blockchain, permitindo designadamente a seleção e avaliação de candidatos com motores e ferramentas muito especificas e diferenciadas

Adapting to unstable and dynamic environments is a critical challenge for organizations. It requires continuous improvements not only in products and services but also in their overall functioning. Rapid shifting in the context creates a need for individuals and work teams to quickly adapt to new conditions and task demands (e.g. Kozlowski & Bell, 2008). The recognition of this new reality has given rise, in the last decade, to a set of theoretical models and empirical research that seek to explain adaptation (e.g. Rosen et al., 2011). Authors have argued that in order to adapt to unexpected situations, teams need to adjust their cognitive and behavioral processes, and emergent states (e.g., Burke et al., 2006). However, a lack of theoretical and empirical integration among different approaches for studying adaptation has constrained the advancement of this field of research. At the empirical level, there is a lack of experimental research and empirical work on the underpinnings of adaptation as a dynamic process, as well as a lack of longitudinal designs that analyze how team performance and adaptation occurs over time (Baard et al., 2014). Finally, although organizations increasingly rely on multiteam systems (MTS) to accomplish their goals (i.e., “two or more teams that interface directly and interdependently in response to environmental contingencies toward the accomplishment of collective goals”, Mathieu et al., 2001, p. 290), research has not empirically analyzed how teams coordinate their work in order to adapt and perform over time. We propose four interrelated empirical studies, combining research methods and approaches to capture the dynamics of team cognition on team adaptation and performance trajectories. We also investigate team cognition and leadership as two relevant coordinating mechanisms that support team adaptation in multiteam systems. In study 1 we will experimentally manipulate shared mental models (SMM) and team cognitive flexibility in o...