Latent class membership can be used to predict a distal outcome (an outcome at a later time). The Methodology Center was at the forefront of research on LCA with a distal outcome for several years. In 2017, we developed a SAS macro and Stata function that estimate LCA with a distal outcome using the BCH approach. This is the approach that we currently recommend for LCA with a distal outcome. You can download the macros on the Software Downloads page.
More information is coming soon, including code to predict an outcome from latent class membership! Stay tuned and sign up for our listserv below.