Aoife O'Neill

Research Interests

Latent Variable Modelling:
My main research focus is the application of latent class analysis to longitudinal survey data in the social, behavioural and health sciences. Latent class analysis (LCA) is a statistical tool that behavioural scientists are using with increasing frequency. LCA provides a framework for measuring categorical variables with the aim of identifying underlying subgroups in a population and classifying individuals into distinct homogeneous groups based on some underlying characteristics. Two useful extensions of LCA are multiple-group LCA and LCA with covariates. Multiple-group LCA allows the researcher to identify differences in groups across the latent unobserved categorical variable, while LCA with covariates extends the model to include predictors of class membership using a logistic link. A benefit of latent class theory is that it can be used to describe the sequential development of process and predict initial status and transitions over time in longitudinal datasets.