Course description

Many psychological characteristics or constructs cannot be measured directly. They are latent variables, which can only be measured indirectly using, for example, items of tests or questionnaires. Using latent variable models, we can measure these constructs, evaluate how well (or precisely) they are measured, how they change over time, and/or how they are associated with other variables.

Two frameworks for latent variable modeling are Structural Equation Models (SEM) and Item Response Theory (IRT). This course offers a theoretical and practical introduction to SEM and IRT models. Several latent variable model types will be discussed, including: path analysis, confirmatory factor analysis, IRT and ordered categorical item response models, measurement invariance (a.k.a. differential item functioning), basic latent growth curve models and cross-lagged panel analyses.

Objectives

1. Translating substantive psychological theories into LVMs, fitting the LVMs and interpreting the results.
2. Acquiring basic skills in fitting LVM models using R package lavaan (short for LAtent VAriable ANalysis).

Contents

Consecutive sessions will cover:

• basic path models,
• confirmatory factor analysis,
• growth curve and cross-lagged panel analyses,
• categorical and ordered-categorical variables (e.g., dichotomous responses, Likert scales), and
• multiple-group analyses. 

For the last session of the course, participants are invited to submit one or more requests on specific analyses, research questions or data structures they encounter in their own research.

Preparation

Get a (digital or physical) copy of the Beaujean book. Install R, R studio and R package lavaan on your laptop. Some basic relaxation exercises.

Every session will be composed of lectures, exercises (fitting LVMs with R package lavaan), and discussion (on how to interpret results).

Literature

Beaujean, A. A. (2014). Latent variable modeling using R a step-by-step guide. Routledge.

Entry requirements

• Basic knowledge and experience with statistical analyses (e.g., linear & logistic regression, factor analysis and/or PCA, reliability analysis).
• Basic proficiency in R: participants are advised to have taken the course ‘Introduction to R’, or should otherwise make sure that their R programming skills are at a similar level.

Fees

Target group	One day	Two days	Three days
PhD candidates FSW	FREE	FREE	FREE
Staff FSW	€300	€400	€500
Other Leiden University PhD candidates	€215	€315	€415
Externals*	€450	€600	€750

*Externals are PhD candidates related to staff members of FSW ("buitenpromovendi") and/or staff members of other Leiden University Faculties.