Kevin M. King @kevinmking.bsky.social · 20/06/20253) latent classes are probabilistic. Everyone in your sample has a chance of being in every class. But often people want to understand predictors, so they often assign ppl to the most likely class, which can be problematic. 2122
Kevin M. King @kevinmking.bsky.social · 20/06/20254) LCGAs are really biased by skew. Guess what a lot of people want to study with LCGAs? Skewed data like substance use in teens or problematic screen use. psycnet.apa.org/journals/met...psycnet.apa.orgAPA PsycNet 1152
Kevin M. King @kevinmking.bsky.social · 20/06/20255) LCGAs also are very sensitive to lots of other things, like the time scale you study, what time intervals you select, or the scale of your data. psycnet.apa.org/record/2006-... psycnet.apa.org/fulltext/200...psycnet.apa.orgAPA PsycNet 1112
