Developmental Methods Conference Johathan

Workshop 1:

An Introduction to Bayesian Estimation with Mplus

Jonathan L. Helm, Ph.D.
Assistant Professor of Quantitative Psychology
San Diego State University

Applications of Bayesian estimation within psychological science have grown exponentially throughout the past two decades. These come as a contrast to frequentist (i.e., maximum likelihood) estimation, which remains dominant in the field. Although many psychological scientists are aware of these two separate approaches, far fewer understand their differences. This workshop introduces attendees to the philosophical, conceptual, and technical* differences that underlie frequentist and Bayesian estimation. In particular, attendees will see how the different philosophies lead to different estimation approaches, and how the different estimation approaches can behave differently. Three empirical examples will illustrate the similarities and differences between the approaches, which will all be conducted via Mplus (example scripts and data sets will be made available). By the workshops end, attendees will be able to characterize the conceptual differences between Bayesian and frequentist estimation, and independently perform Bayesian estimation using Mplus.

*The technical part will be very light! You will understand everything!

Workshop 2:

Growth Modeling: Pushing into Nonlinearity

Nilam Ram, Ph.D.
Professor, Human Development and Family Studies
Penn State University

This workshop discusses nonlinear growth models from the multilevel and structural equation modeling perspectives. Growth models have become a mainstay of longitudinal data analysis in the social and behavioral sciences to examine how individuals change over time and how individuals differ in their change process. This advanced workshop will cover the following topics: overview of the definition of nonlinearity with respect to growth models, growth models that are nonlinear with respect to time, parameters, and random coefficients. Code examples provided in R.

Niall Bolger Professor of Psychology

Workshop 3:

Intensive Longitudinal Methods: An Introduction to Diary and Experience Sampling Research

Niall Bolger, Ph.D.
Professor of Psychology
Columbia University

Intensive longitudinal methods, often called experience sampling, daily diary, or ecological momentary assessment methods, allow researchers to study people’s thoughts, emotions, and behaviors in their natural contexts. Typically, they involve self-reports from individuals, dyads, families or other small groups over the course of hours, days, and weeks. Such data can reveal life as it is actually lived and provide insights that are not possible using conventional experimental or survey research methods. Intensive longitudinal data, however, present data analytic challenges stemming from the multiple levels of analysis and temporal dependencies in the data. In this half-day workshop, participants will (a) recognize the types of research questions that can be addressed using intensive longitudinal methods; (b) see example datasets and how to run basic longitudinal models using SPSS Mixed and Mplus; and (c) understand in broad strokes how complex topics such as dyadic, mediation, and power analyses can be handled using Mplus. We will assume that participants are familiar with multiple regression analysis and ANOVA.

RECOMMENDED READING: Bolger, N. & Laurenceau, J-P. (2013). Intensive longitudinal methods: An introduction to diary and experience sampling research. New York: Guilford.

Data sets and syntax for analyses can be found here:

Karen Nylund-Gibson Professor California Santa Barbara

Workshop 4:

Introduction to Latent Transition Analysis in Mplus

Karen Nylund-Gibson, Ph.D.
Associate Professor, Graduate School of Education
University of California, Santa Barbara

This half day course will introduce participants to latent transition analysis (LTA) and its specification in Mplus.  We will highlight how the LTA model addresses longitudinal change and how it is different than growth models.  The implementation and interpretation of the LTA model be demonstrated throughout the course.  Some familiarity with latent class and latent profile models in Mplus would be desirable, but not required.