IHMJ2206 Latent profile analysis with covariates and distal outcomes (2 cr)

Latent Profile Analysis (LPA) is a subset of the broader General Latent Variable Modelling framework. It is commonly used to group subjects into categories that reflect underlying patterns in the data. In addition to this, LPA offers a versatile approach applicable in various settings, including longitudinal studies.

In this course, you will be introduced to the key concepts of LPA, including understanding what LPA is, how to run models using Mplus, selecting between different models, classifying observations, and assessing and predicting classifications. You will also explore more advanced models, particularly those that examine the relationships between specified latent profiles, covariates, and distal outcomes.

The following topics will be covered in the course:

· Introduction to LPA: - Introduction to mixture modelling

- Definition of latent class analysis and LPA - Specification of LPA models in Mplus

- Assessment of model fit

- Model comparisons

- Applications of LPA with actual data

- Reporting results of LPA

· LPA with covariates and distal outcomes: - Understanding the concept of measurement equivalence

- Definition of covariates and distal outcomes

- Logistic regression analysis - LPA with covariates using the R3STEP in Mplus

- LPA with distal outcomes using the BCH method in Mplus

- Applications of the R3STEP and BCH method with actual data

- Challenges and potential avenues for further exploration

Learning outcomes: By the end of this module, students will be able to:

· Understand the basic concepts and theories related to LPA

· Understand the practical foundations of LPA and its relationship between covariates or distal outcomes

· Apply and implement LPA using Mplus

Prerequisites: Basic concepts of statistics (e.g., understanding of different types of variables, normal distribution, hypothesis testing, and correlation)

Prerequisites: Basic concepts of statistics (e.g., understanding of different types of variables, normal distribution, hypothesis testing, and correlation)