Using Principal Components and Factor Analysis in Animal Behaviour Research: Caveats and Guidelines

By S. Budaev. 2010

432 citations recorded by the source corpus.

Subfields: Animal Science and Zoology, Ecology, Evolution, Behavior and Systematics, Genetics

View Paper: https://www.semanticscholar.org/paper/7ef48b8098d4a001182f7901b4af45f66d79695a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Animal Science and Zoology

In Ecology, Evolution, Behavior and Systematics

In Genetics

Citations in the corpus

Statistical Issues and Assumptions of Phylogenetic Generalized Least Squares (2014, methodology): “…to combine predictors (Freckleton 2011) using, for instance, a principal component or factor analysis and use the derived (principal component or factor) scores rather than the original covariates (e.g., Quinn and Keough 2002; for more about principal component or factor analysis, see Budaev 2010).”
Are there differences between behavioral measurement methods? A comparison of the predictive validity of two ratings methods in a working dog program (2012, neutral): “We tested the sampling adequacy of both PCAs using the Bartlett sphericity test and the Kaiser–Meyer–Olkin (KMO) measure (Budaev, 2010).”
Development and application of CatFACS: Are human cat adopters influenced by cat facial expressions? (2017, methodology): “Since there were no initial assumptions about the data collected or the nature of the variables, an Exploratory Factor Analyses (EFA, e.g. Budaev, 2010; Williams et al., 2010) was performed with 36 Behavioural Variables in order to reduce data complexity, while retaining as much of the original…”
Glucocorticoid-Mediated Phenotypes in Vertebrates : Multilevel Variation and Evolution (2016, background): “…but spurious repeatability in “change in corticosterone”; and (2) performing “statistics on statistics” can inflate type 1 error rates because the uncertainty around the estimate of an individual’s flexibility is discarded (Budaev, 2010; Dingemanse & Dochtermann, 2013; Nakagawa & Schielzeth, 2010).”
Social personality traits in chimpanzees: temporal stability and structure of behaviourally assessed personality traits in three captive populations (2011, positive): “FA is a data reduction tool used to assess an unobservable latent construct that accounts for correlations amongst variables; it is preferable to principal components analysis when the aim is to interpret and label the emerging factors (Budaev 2010).”
Behaviour and experiences of dogs during the first year of life predict the outcome in a later temperament test (2014, methodology): “(KMO) measure (Budaev, 2010) and the correlation matrix of the standardised T-test”