Teach Yourself LCA

How to use the LCA Learning Path

LCA diagram with no words. The latent construct is represented by an oval. Arrows point from the oval to 4 rectangles. The rectangles are the manifest constructs that help measure the latent construct. The arrows point toward the boxes because the manifest variables are representations of the underlying latent construct. The videos, links, and SAS code below are designed to allow SAS users to teach themselves how to plan, run, and interpret latent class analysis (LCA). This page is designed for users of all levels to be able to jump in wherever they need information. Within each section, there may be different ways to get the same information (e.g., watching a video, listening to a podcast, or running a SAS exercise). Users who possess basic familiarity with a given subject may want to download and run SAS code immediately. Users who are new to a subject may want to watch a video before running the relevant code.

All materials are designed for researchers who are new to LCA but who do have some familiarity with SAS. In other words, this is an LCA tutorial, not a SAS tutorial.

If you want to follow along with the examples below, you will need a computer that runs Windows with an installation of SAS 9.2 or higher. You will also need to download PROC LCA. We also offer the LCA Plugin for Stata users, but these materials focus primarily on our SAS procedure.

Conceptual Introduction to LCA

Latent class modeling refers to a group of techniques for identifying unobservable, or latent, subgroups within a population. Methodology Center researchers have developed and expanded methods like latent class analysis (LCA) and latent transition analysis (LTA) over the last two decades. The Methodology Center maintains a number of resources for introducing LCA.

video: Overview (6 minutes)
pptx: Introduction to LCA (part of the LCA Teachers’ Corner instructional download)
webpage: Introductory example: Profiles of Teen Sex and Drug Use

Detailed Introduction

If you have a conceptual understanding of LCA, these resources can help you develop a comprehensive understanding of how the method can be and has been applied.

video: Webinar with Bethany Bray (2 hours)
articles: Recommended publications to introduce LCA
webpage: LCA example: Profiles of Teen Sex and Drug Use

webpage: webpage: LCA FAQ
webpage: LCA and LTA Book by Linda Collins and Stephanie Lanza
podcast: Common Questions about LCA
podcast: Advanced Topics in LCA

LCA and LTA Software

The Methodology Center offers free LCA software for use with SAS and Stata. (The SAS procedure can also accommodate LTA, but the Stata plugin cannot.) Free packages that perform LCA in R are available on CRAN. Commercial options like Latent GOLD and Mplus also available.

This video introduces how to use PROC LCA and PROC LTA for SAS. A full installation of SAS is required to use these procedures; they will not work with SAS Enterprise Guide. Consult the PROC LCA download page to learn more about which version of the PROC to install.

The video describes the standard syntax for PROC LCA and a few options including grouping variables and covariates. This content is also described in the PROC LCA and PROC LTA Users’ Guide.

LCA With a Grouping Variable and/or Covariates

This section from the webinar embedded in the Detailed Introduction section above describes how to incorporate grouping variables (e.g., biological sex) into an LCA.

Immediately following that section is an explanation of how to incorporate covariates into an LCA at 48:57.

See appendix 5 in the PROC LCA & PROC LTA Users’ Guide for example SAS code.

Latent Transition Analysis (LTA)

Latent Transition Analysis (LTA) is a longitudinal extension of LCA. We have several resources dedicated to introducing this method. On the left is a 2-hour webinar that introduces the basics of LTA.

video: Overview of LTA (15-minutes)
podcast: Advanced Topics in LCA (addresses LTA along with other topics)
webpage: LCA & LTA FAQ
webpage: Change in teen sexual risk example
webpage: LCA and LTA Book by Linda Collins and Stephanie Lanza
articles: Recommended readings to introduce LCA and LTA