The LCAKB’s Code Repository is designed to be a “one-stop shop” to download sample code for latent class models. Many of the code examples come from projects and workshops conducted by Drs. Bethany Bray, John Dziak, and Stephanie Lanza when they were investigators at The Methodology Center at Penn State and supported in part by National Institute on Drug Abuse Center of Excellence awards from 1996-2021 (P50 DA039838 and P50 DA010075). In addition, many of the code examples come from the work of their collaborators and trainees, including those supported by the Prevention and Methodology Training Program, a National Institute on Drug Abuse Training Program (T32 DA017629).
Below you will find a list of all available models and code “snippets.” You can use the filters on the sidebar to narrow down the models for which you are looking. The LCAKB Code Repository is under active development and is currently being expanded. New models and code snippets will be published soon. Please sign up to our mailing list below to be informed of when they are published. If you would like to contribute a piece of code to help your fellow researchers, please email Dr. Bethany Bray at email@example.com.
LCA: Baseline LCA with all binary indicators
This code fits a 4-class, baseline, latent-class model for marijuana use and attitudes using 7 binary indicators of the latent class variable. This code also plots the item-response probabilities using a line graph.
LCA: LCA with a grouping variable and measurement invariance
This code fits a 4-class, latent-class model for marijuana use and attitudes using 7 binary indicators of the latent class variable. It includes a grouping variable for year, and observations came from 3 different years.
LPA: Baseline LPA with all continuous indicators
This code fits a 5-class, baseline, latent-profile model for the “Big 5” personality traits using 5 continuous indicators of the latent class variable.
LTA: Baseline LTA with 2 times, all binary indicators, and measurement invariance
This code fits a 2-time, 5-class, latent-transition model for delinquency over time using 6 binary indicators of the latent class variable. Measurement invariance across time is imposed such that analogous item-response probabilities within classes are restricted to be equal to each other across times.
Let’s stay in touch.
We are in this together. Receive an email whenever a new model or resource is added to the Knowledge Base website.