The network structure of schizotypy in the general population

Abstract

Schizotypal personality traits show similarity with schizophrenia at various levels of analysis. It is generally agreed that schizotypal personality is multidimensional; however, it is still debated whether impulsive nonconformity should be incorporated into theories and measurement of schizotypy. In addition, relatively little is known about the network structure of the four-dimensional model of schizotypal personality. To estimate the network structure of schizotypy, we used data from participants recruited from the community (N = 11,807) who completed the short version of the Oxford-Liverpool Inventory of Feelings and Experiences, a widespread self-report instrument that assesses the positive, negative, disorganised and impulsive domains of schizotypy. We performed community detection, then examined differences between communities in terms of centralities and compared the strength of edges within and between communities. We found communities that almost perfectly corresponded to the a priori-defined subscales (93% overlap, normalised mutual information = 0.74). Items in the disorganisation community had higher closeness centrality relative to items in the other communities (Cliff's Δs ranged from 0.55 to 0.83) and weights of edges within the disorganisation community were stronger as compared to the negative schizotypy and impulsive nonconformity communities (Cliff's Δs = 0.33). Our findings imply that the inclusion of impulsive nonconformity items does not dilute the classical three-factor structure of positive, negative and disorganised schizotypy. The high closeness centrality of disorganisation concurs with theories positing that cognitive slippage and associative loosening are core features of the schizophrenic phenotype.

Keywords: Factor structure; Network analysis; Personality; Schizophrenia; Schizotypy.

Fig. 1

The network structure of schizotypy, as measured with the sO-LIFE in a large online community sample. Nodes represent items and edges represent conditionally independent relationships between items. Node colours indicate communities. Positive edges are shown in grey and negative edges are shown in red. Edge width reflects edge weight, node border width reflects node betweenness, and node size reflects node closeness

Fig. 2

Distribution of z-standardised of node closeness, betweenness and expected influence centralities. On the left side of the panels, the nodes are sorted in a descending rank order; while on the right side, the distribution of the z-standardised centrality scores are shown by community

Fig. 3

Weights of edges that are located within (top) and between (bottom) communities. In the bottom panel, the colour of the points and the boxplot indicates the community pair whose connection strength is shown. Note that the network is undirected and mapping of community to points vs. boxplots is arbitrary