Abstract
Studies of animal personality attempt to uncover underlying or “latent” personality traits that explain broad patterns of behaviour, often by applying latent variable statistical models (e.g., factor analysis) to multivariate data sets. Two integral, but infrequently confirmed, assumptions of latent variable models in animal personality are: i) behavioural variables are independent (i.e., uncorrelated) conditional on the latent personality traits they reflect (local independence), and ii) personality traits are associated with behavioural variables in the same way across individuals or groups of individuals (measurement invariance). We tested these assumptions using observations of aggression in four age classes (4–10 months, 10 months–3 years, 3–6 years, over 6 years) of male and female shelter dogs (N = 4,743) in 11 different contexts. A structural equation model supported the hypothesis of two positively correlated personality traits underlying aggression across contexts: aggressiveness towards people and aggressiveness towards dogs (comparative fit index: 0.96; Tucker-Lewis index: 0.95; root mean square error of approximation: 0.03). Aggression across contexts was moderately repeatable (towards people: intraclass correlation coefficient (ICC) = 0.479; towards dogs: ICC = 0.303). However, certain contexts related to aggressiveness towards people (but not dogs) shared significant residual relationships unaccounted for by latent levels of aggressiveness. Furthermore, aggressiveness towards people and dogs in different contexts interacted with sex and age. Thus, sex and age differences in displays of aggression were not simple functions of underlying aggressiveness. Our results illustrate that the robustness of traits in latent variable models must be critically assessed before making conclusions about the effects of, or factors influencing, animal personality. Our findings are of concern because inaccurate “aggressive personality” trait attributions can be costly to dogs, recipients of aggression and society in general.
Highlights
Because behavioural variables comprising personality traits are expected to correlate with each other [4], the utility of formative models to revealing underlying personality traits has been criticised in both animals [12,13] and humans [10,11,14,15]
To test for measurement invariance in each of the latent traits derived from the best fitting structural equation model, we investigated the response patterns across aggression contexts related to the same latent aggressiveness trait using Bayesian hierarchical logistic regression models
This study has tested the assumptions of local independence and measurement invariance of personality traits in shelter dogs
Summary
Measurement biases in aggressiveness in dogs before the research began. This does not alter our adherence to PLOS ONE policies on sharing data and materials. To interpret the complexity inherent in behavioural phenotypes, personality traits and behavioural syndromes are frequently inferred using latent variable statistical models [6], which reduce two or more measured variables (the manifest variables) into one or more lower-dimensional variables (the latent variables), following work in human psychology [7,8,9,10]. Many animal personality studies use formative models, such as principal components analysis, that construct composite variables comprised of linear combinations of manifest variables. Reflective models regress measured behaviours on one or more latent variables, incorporating measurement error and possibilities to compare a priori competing hypotheses [1,16,19]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
