Short Courses For IMPS 2019

Structural equation modeling with lavaan

Instructor: Yves Rosseel

Yves Rosseel

This workshop will provide both a refresher of SEM concepts and practices, and a tutorial on how to use the open-source R package lavaan for SEM (http://lavaan.org). After a brief general introduction to SEM, several specific topics will be discussed: mean structures and multiple groups, measurement invariance, dealing with missing data and non-normal data, dealing with binary and ordinal data, longitudinal SEM (for a small number of time points), and multilevel SEM. The workshop will be based on lecture-style presentations interchanged with practical sessions. The intended audience for the workshop is undergraduate/graduate students, faculty, researchers, and anyone who is interested in structural equation modeling. The workshop is also useful for those who have been using commercial software for SEM, and are interested in switching to open-source software. Some prior experience with R is useful, but not necessary.

 

Introducción al análisis de clases latentes y los modelos de mezclas

Instructor: Jeroen Vermunt

Jereon Vermunt

El análisis de clases latentes (Latent Class Analysis, ACL) se ha existido desde la década de 1950 como método para encontrar agrupaciones o construir tipologías utilizando un conjunto de variables categóricas observadas. Hoy en día, el ACL es parte de lasherramientas estadísticas utilizadas por los investigadores en psicología y otros campos aplicados.

Este curso presentará los conceptos básicos del modelado de clases latentes, incluyendo: 1) las fórmulas y los supuestos básicos; 2) decidir sobre el número de clases latentes utilizando medidas de bondad de ajuste y criterios de información; 3) clasificar observaciones en clases latentes; y 4) realizar análisis subsiguientes con las clasificaciones usando predictores o variables dependientes.

También se presentarán variantes del modelo básico de ACL que a menudo se denominan “modelos de mezclas” (Mixture Models), que incluyen Modelos de Crecimiento de Mezcla (Mixture Growth Model) para identificar subgrupos en datos longitudinales y Modelos de Mezclas de Distribuciones para agrupar respuestas continuas. Además, se presentarán brevemente modelos más avanzados, tales como el Modelo de Transición Latente (latent transition model) y el Modelo de Clases Latentes Multinivel.

Durante el curso se usará el programa Latent GOLD para ilustrar los métodos con datos reales. Los participantes pueden instalar la versión de demostración en sus propios equipos portátiles para replicar los análisis que se realizarán.

 

JASP

Instructor: Eric-Jan Wagenmakers

Eric-Jan Wagenmakers

 

Applying Test Equating methods using R

Instructors: Marie Wiberg and Jorge González

Marie WibergJorge González

The goal of this workshop is to introduce equating and to provide the necessary tools to be able to perform different equating methods in practice by using available R packages. The aim of test equating is to adjust the test scores on different test forms so that they can be comparable and used interchangeably. Equating has a central role in large testing programs and it constitutes an important step in the process of collecting, analyzing, and reporting test scores. Equating is important as it ensures a fair assessment regardless the time, place or background different test takers might have. Through a number of examples and practical exercises, attendees will get both a conceptual and practical understanding of various equating methods conducted under different data collection designs. The R software will be used throughout the session with special focus on the packages; equate, kequate, SNSequate and equateIRT. The training session follows some of the chapters in the book Applying test equating methods using R which has been written by the instructors and was released in 2017 by Springer.