Latent profile analysis (LPA) is a statistical technique that aims to detect underlying latent groups, called profiles, from observed continuous data. LPA falls under the umbrella of a finite mixture model (FMM). The model estimates the probability of belonging to each latent profile for each participant. This should be viewed in contrast to factor analysis, that takes continuous measures and detects latent continuous factors.
Within this workshop, we will:
- discuss the different decisions one must make while implementing an LPA
- compare LPA to other clustering methods
- discuss several examples of LPAs
- implement an LPA in R