How to interpret centrality values in network structures (not)

For posts on psych-networks, I usually want to write about a topic for a few months, don’t find the time, and then a new paper comes along that prompts me to write up what I had in mind. For instance: A paper by Madhoo & Levin 2016 prompted me to …

Bootstrapping edges after regularization: clarifications & tutorial

I have read the following statement numerous times in the last months: “If the 95% boostrapped CI of an edge weight in a network contains zero, the edge is likely not different from zero”. This is incorrect in case of regularized partial correlation networks, and I thought I would write …

Estimating psychological networks via Information Filtering Networks

TL;DR: This blog post summarizes and discusses Information Filtering Networks introduced in a new paper by Christensen et al. 2018, and discusses them compared to the lasso-regularized Markov Random Fields. The post ends with an R tutorial on how to estimate such networks. Markov Random Fields (MRF) have quickly become …

FAQ on network stability, part II: Why is my network unstable?

In a previous tutorial blog post, I summarized the bootstrapping routine developed by Sacha Epskamp and me that we recommend for testing the stability / accuracy / precision of estimated network models and parameters. This matters a great deal and should be considered a standard step in every empirical network …

Does network connectivity predict future depression? Non-replication paper published

Lizanne Schweren, a Postdoc at the University Medical Center Groningen, and colleagues published a paper in JAMA Psychiatry this morning showing that the connectivity of depression symptoms is, in contrast to what a prior paper found, not a predictor of treatment response. This is the first non-replication in the psychopathology …

Tutorial: how to review psychopathology network papers

The network literature on psychopathology is exploding, which means there are many reviews to be performed. While each paper is different, some common themes have emerged, and because I have been asked on which aspects I focus my reviews and what my current main concerns are, here is a brief …

R tutorial: how to identify communities of items in networks

A problem we see in psychological network papers is that authors sometimes over-interpret the visualization of their data. This pertains especially to the layout and node placement of the graph, for instance: do nodes in the networks cluster in certain communities. Below I will discuss this problem in some detail, …