2024 ISDSA Meeting

Workshops

Three workshops will be available. You will get a certificate of achievement for each workshop after completing it. Each workshop is 3-hour long and taught online through Zoom.

Workshop 1: Conducting Meta-Analytic Structural Equation Modeling with R

Time: 1pm-4pm, July 21, Vienna Time / 8pm-11pm, July 21, Singapore Time / 8am-11am, July 21, US Eastern Time
Location： Virtual on Zoom (Register to get the link)

The workshop will cover meta-analytic structural equation modeling (MASEM), which uses the techniques of meta-analysis and structural equation modeling to synthesize correlation matrices and fit hypothesized models on the combined correlation matrix. It can be used to test path models, confirmatory factor analytic models, and structural equation models from a pool of correlation matrices. MASEM offers the benefits of both meta-analysis and SEM.

During the workshop, I will provide an introduction to the basic theory of MASEM and demonstrate how to conduct the analyses with R. While some familiarity with R would be beneficial, the workshop is designed to be accessible to those who are new to the programming language.

• 

  Mike Cheung -- National University of Singapore

  Professor Mike Cheung specializes in quantitative methods and conducts research in structural equation modeling, meta-analysis, and multilevel modeling. His work focuses on the integration of meta-analysis and structural equation modeling. He is an Associate Editor of Research Synthesis Methods and Neuropsychology Review and serves on the editorial boards of several journals. For more information, please visit https://mikewlcheung.github.io/.

Workshop 2: An Introduction to Generalized Structured Component Analysis Structural Equation Modelling (GSCA-SEM) and its Applications Using Free Software

Time: 7pm-10pm, July 21, Vienna Time / 1pm-4pm, July 21, US/Canada Eastern Time
Location： Virtual on Zoom (Register to get the link)

Researchers in various fields are interested in studying the path-analytic relationships between constructs such as self-esteem, depression, socioeconomic status, etc. As constructs are abstract concepts that are not directly measurable, they are represented by proxies linked to empirical data or observed variables in statistical models. This enables researchers to test hypotheses about the relationships between constructs. There are two traditional ways of statistically representing constructs: (common) factors and components.

Structural equation modelling (SEM) is a general statistical framework for specifying and examining how such statistical representations as factors or components are related to observed variables and how they are related based on prior theory or knowledge. SEM has diverged into two domains, i.e., factor-based vs. component-based, depending on whether all constructs are represented as factors or components.

The two SEM domains include different statistical methods. Covariance structure analysis (CSA) has been a standard method for factor-based SEM, although there are other methods, including model-implied instrumental variable methods, factor score regression, structured factor analysis, and generalized structured component analysis with measurement errors incorporated (GSCA M ) . On the other hand, generalized structured component analysis (GSCA) is the most general method for component-based SEM, which can include a long- standing component-based method, partial least squares path modelling, as a special case. It has been shown that when an SEM method developed for one domain is used for the other domain, it results in biased solutions. For example, CSA will provide biased estimates of parameters in models with components (e.g., component loadings and path coefficients relating components), whereas GSCA will yield biased estimates of parameters in models with factors (e.g., factor loadings and path coefficients connecting factors).

Over the decades, all the methods have been used exclusively for either of the two SEM domains, permitting researchers to estimate models with factors or components only. However, researchers may often need to include both factors and components in the model to consider a broad array of constructs from different disciplines. The next generation of SEM methods has recently emerged that permits estimating models with both factors and components in a unified framework. It includes consistent partial least squares and integrated generalized structured component analysis (IGSCA).

GSCA-SEM (generalized structured component analysis structural equation modelling) is an umbrella term that includes three SEM methods—GSCA, GSCA M , and IGSCA—for estimating models with components only, with factors only, or with both factors and components, respectively. GSCA-SEM is highly versatile in accommodating the two statistical representations of constructs. GSCA Pro is a stand-alone software program for GSCA-SEM. The software can be freely downloaded from its website (www.gscapro.com). It provides a graphical user interface that allows users to draw their model as a path diagram easily, fit GSCA-SEM to the model, and obtain results.

This workshop begins by explaining the conceptual foundations of GSCA-SEM, focusing on model specification and evaluation. It then provides step-by-step illustrations of using the free software for various GSCA-SEM applications.

• 

  Heungsun Hwang -- McGill University

  Prof. Hwang’s research program is generally devoted to the development and application of quantitative methods to address diverse issues in psychology and various other fields. His recent interests include the development of data integration tools for high-dimensional data collected from multiple sources; the development of a statistical methodology for investigating associations among genetic, brain, and behavioural/cognitive phenotypes; and the development and application of predictive models or machine learning algorithms for predicting behavioural and cognitive outcomes using genetic, physiological, and psychological data.

Workshop 3: Causal Moderated Mediation Analysis

Time: 1pm-4pm, July 24, Vienna Time / 8pm-11pm, July 24, Singapore Time / 8am-11am, July 24, US Eastern Time
Location： Virtual on Zoom (Register to get the link)

Research questions regarding how, for whom, and where a treatment achieves its effect on an outcome have become increasingly valued. Such questions can be answered by causal moderated mediation analysis, which assesses the heterogeneity of the mediation mechanism underlying the treatment effect across individual and contextual characteristics. The purpose of this three-hour virtual course is to introduce the general definition, identification, estimation, and sensitivity analysis for causal moderated mediation effects under the potential outcomes framework. Participants will also learn how to use a user-friendly R package to conduct the analysis and visualize analysis results. The method introduction and the package implementation will be illustrated with a re-analysis of the National Evaluation of Welfare-to-Work Strategies (NEWWS) Riverside data.

• 

  Xu Qin -- University of Pittsburgh

  Dr. Xu Qin is an Assistant Professor of Research Methodology at the School of Education (primary) and an Assistant Professor of Biostatistics at the School of Public Health (secondary). She holds a Ph.D. from the Department of Comparative Human Development at the University of Chicago and a B.S. and an M.S. in Statistics from the Renmin University of China.
  
  Her research focuses on solving cutting-edge methodological problems in causal mediation analysis and multilevel modeling. She is also interested in using rigorous and innovative quantitative methods to evaluate the impacts of interventions and the underlying mechanisms. Methodologically, she has developed statistical methods and software for investigating the heterogeneity in causal mediation mechanisms in both multilevel and single-level settings, as well as sensitivity analysis and power analysis methods for causal mediation analysis. Substantively, she is interested in applying advanced statistical methods in developmental, educational, and health research.