Latent Transition Analysis - Online Course
Friday, April 9 —
Saturday, April 10, 2027
10:30am-12:30pm (convert to your local time)
1:00pm-3:00pm
Latent class and latent profile analysis (LCA and LPA) have proven to be useful tools for researchers in the social, behavioral, and health sciences to understand hidden structures and patterns in their data. For example, you can use these methods to identify subgroups of participants who share similar patterns of behaviors or attitudes. LCA and LPA can also provide a more nuanced understanding of the ways in which intersecting behaviors confer higher risk of adverse outcomes. Latent transition analysis (LTA) extends LCA and LPA to longitudinal data, allowing you to examine changes in subgroup membership over time.
LCA and LPA can be viewed as special kinds of structural equation models in which the latent variables are categorical rather than continuous. These methods can uncover hidden structures and patterns related to multidimensional phenomena. LCA and LPA were originally developed to measure static, categorical, latent constructs. That is, they were developed to measure constructs that do not change over time or constructs measured at only one occasion. However, developmental questions about change over time in multidimensional phenomena measured as categorical latent constructs can be addressed by examining incidences of transitions over time in subgroup membership (i.e., class or profile membership). This method is known as LTA.
By using LTA to model changes in complex, multidimensional latent constructs over time, you can gain a more comprehensive understanding of the developmental phenomena you’re investigating. Applying this method to empirical data can inform theory, contribute to evidence-based decision-making, and shed light on heterogeneity in the effects of interventions. Ultimately, LTA empowers researchers in the social, behavioral, and health sciences to gain new insights from their longitudinal data and contribute innovative findings that advance science.
This seminar will give you the theoretical background and applied skills to address interesting research questions using LTA applied to longitudinal panel data. Topics include model identification, model selection, model interpretation, measurement invariance across time, multiple-groups models, and predicting transitions over time in subgroup membership, as well as comparing LTA to other longitudinal models for panel data (e.g., growth curve models, growth mixture models). The format will combine lectures, software demonstrations, computer exercises, and discussion. There will be opportunities to discuss how LTA can be applied in your research.
Starting April 9, this seminar will be presented as an 8-hour synchronous, livestream workshop via Zoom. Each day will feature two lecture sessions with hands-on exercises, separated by a 30-minute break. Live attendance is recommended for the best experience. If you can’t join in real time, recordings will be available within 24 hours and accessible for four weeks after the seminar.
Closed captioning is available for all live and recorded sessions. Captions can be translated to a variety of languages, including Spanish, Korean, and Italian. For more information, click here.
ECTS Equivalent Points: 1
Computing
All examples and exercises will be demonstrated using Mplus (version 8.11, with the Combination add-on). If you don’t have access to Mplus during the seminar, you can follow along using the provided materials as the instructors complete each exercise. You will receive copies of all lecture slides and all syntax and output used during the seminar. Syntax and output will also be provided in Latent Gold and SAS whenever possible.
Previous experience with estimating latent class models in Mplus is recommended but not required. Basic familiarity with Mplus is helpful, but even novice Mplus users will be able to follow the lectures and complete the exercises.
If you’d like to familiarize yourself with Mplus basics before the seminar begins, we recommend reading through UCLA’s short guide here.
All examples and exercises will be demonstrated using Mplus (version 8.11, with the Combination add-on). If you don’t have access to Mplus during the seminar, you can follow along using the provided materials as the instructors complete each exercise. You will receive copies of all lecture slides and all syntax and output used during the seminar. Syntax and output will also be provided in Latent Gold and SAS whenever possible.
Previous experience with estimating latent class models in Mplus is recommended but not required. Basic familiarity with Mplus is helpful, but even novice Mplus users will be able to follow the lectures and complete the exercises.
If you’d like to familiarize yourself with Mplus basics before the seminar begins, we recommend reading through UCLA’s short guide here.
Who should register?
If you are a researcher familiar with latent class analysis (LCA) and/or latent profile analysis (LPA) who wishes to extend your understanding to the analysis of longitudinal panel data using latent transition analysis (LTA), this seminar is for you. You will learn the theoretical and practical fundamentals of LTA, how to estimate and interpret latent transition models, and how to predict transitions between latent classes/profiles over time.
Previous attendance at Statistical Horizons’ Latent Class Analysis seminar is recommended but not required. To get the most out of this seminar, you should have a working knowledge of the principles and practices of LCA and/or LPA.
If you are a researcher familiar with latent class analysis (LCA) and/or latent profile analysis (LPA) who wishes to extend your understanding to the analysis of longitudinal panel data using latent transition analysis (LTA), this seminar is for you. You will learn the theoretical and practical fundamentals of LTA, how to estimate and interpret latent transition models, and how to predict transitions between latent classes/profiles over time.
Previous attendance at Statistical Horizons’ Latent Class Analysis seminar is recommended but not required. To get the most out of this seminar, you should have a working knowledge of the principles and practices of LCA and/or LPA.
Seminar outline
Day 1: Introduction to latent transition analysis (LTA)
-
- Brief overview of latent class analysis (LCA)
- Conceptual introduction to LTA
- Parameters estimated in LTA
- Technical considerations: model identification, model selection
Day 2: Adding features to a latent transition model
-
- Technical considerations: measurement invariance across time
- Including a grouping variable
- Predicting Time 1 latent class/profile membership
- Predicting Time t to Time t+1 transitions over time
- Comparing LTA to other longitudinal models for panel data (e.g., growth curve modeling, growth mixture modeling)
Day 1: Introduction to latent transition analysis (LTA)
-
- Brief overview of latent class analysis (LCA)
- Conceptual introduction to LTA
- Parameters estimated in LTA
- Technical considerations: model identification, model selection
Day 2: Adding features to a latent transition model
-
- Technical considerations: measurement invariance across time
- Including a grouping variable
- Predicting Time 1 latent class/profile membership
- Predicting Time t to Time t+1 transitions over time
- Comparing LTA to other longitudinal models for panel data (e.g., growth curve modeling, growth mixture modeling)
Payment information
The fee of $695 USD includes all course materials.
PayPal and all major credit cards are accepted.
Need funding from your employer or institution? Use our funding request template.
Our Tax ID number is 26-4576270.
The fee of $695 USD includes all course materials.
PayPal and all major credit cards are accepted.
Need funding from your employer or institution? Use our funding request template.
Our Tax ID number is 26-4576270.