We have a new commentary in Molecular Psychiatry entitled “Problems with latent class analysis to detect data-driven subtypes of depression” (PDF; together with the fantastic Hanna van Loo, Rob Wanders & Klaas Wardenaar).
This was a response to numerous papers over the last years that found separate latent classes in depression that may be statistical artifacts and driven by violations of local independence.
ยป van Loo, H. M., Wanders, R. B. K., Wardenaar, K. J., & Fried, E. I. (2016). Problems with latent class analysis to detect data-driven subtypes of depression. Molecular Psychiatry. (PDF)