Bayesian Uncertainty Estimation for Gaussian Graphical Models and Centrality Indices

Testing Conditional Independence in Psychometric Networks: An Analysis of Three Bayesian Methods

Network psychometrics uses graphical models to assess the network structure of psychological variables. An important task in their analysis is determining which variables are unrelated in the network, i.e., are independent given the rest of the network variables. This conditional independence structure is a gateway to understanding the causal structure underlying psychological processes. Thus, it is crucial to have an appropriate method for evaluating conditional independence and dependence hypotheses. Bayesian approaches to testing such hypotheses allow researchers to differentiate between absence of evidence and evidence of absence of connections (edges) between pairs of variables in a network. Three Bayesian approaches to assessing conditional independence have been proposed in the network psychometrics literature. We believe that their theoretical foundations are not widely known, and therefore we provide a conceptual review of the proposed methods and highlight their strengths and limitations through a simulation study. We also illustrate the methods using an empirical example with data on Dark Triad Personality. Finally, we provide recommendations on how to choose the optimal method and discuss the current gaps in the literature on this important topic.

Integrating clinician and patient case conceptualization with momentary assessment data to construct idiographic networks: Moving toward personalized treatment for eating disorders

Eating disorders are serious psychiatric illnesses with treatments ineffective for about 50% of individuals due to high heterogeneity of symptom presentation even within the same diagnoses, a lack of personalized treatments to address this heterogeneity, and the fact that clinicians are left to rely upon their own judgment to decide how to personalize treatment. Idiographic (personalized) networks can be estimated from ecological momentary assessment data, and have been used to investigate central symptoms, which are theorized to be fruitful treatment targets. However, both efficacy of treatment target selection and implementation with 'real world' clinicians could be maximized if clinician input is integrated into such networks. An emerging line of research is therefore proposing to integrate case conceptualizations and statistical routines, tying together the benefits from clinical expertise as well as patient experience and idiographic networks. The current pilot compares personalized treatment implications from different approaches to constructing idiographic networks. For two patients with a diagnosis of anorexia nervosa, we compared idiographic networks 1) based on the case conceptualization from clinician and patient, 2) estimated from patient EMA data (the current default in the literature), and 3) based on a combination of case conceptualization and patient EMA data networks, drawing on informative priors in Bayesian inference. Centrality-based treatment recommendations differed to varying extent between these approaches for patients. We discuss implications from these findings, as well as how these models may inform clinical practice by pairing evidence-based treatments with identified treatment targets.