Each HLM workshop covers basics and applications of multilevel modeling with extensions to more complex designs. Participants will learn how to analyze both organizational and longitudinal (growth curve) data using multilevel
modeling and to interpret the results from their analyses. Although the workshop does not require any prior knowledge or experience with multilevel modeling, participants are expected to have a working knowledge of multiple regression as well as SPSS (or SAS).
Analyses will be demonstrated using the software HLMv7. Instruction will consist of lectures, computer workshops, and individualized consultations. The workshop emphasizes practical applications and places minimal emphasis on statistical theory.
The workshop on dyadic data analysis will focus on data where both members of a dyad are measured on the same set of variables. Among the topics to be covered are the measurement of nonindependence, the actor-partner
interdependence model, the analysis of distinguishable and indistinguishable dyads, mediation and moderation of dyadic effects, and over-time analyses of dyadic data. The software package used in the workshop will be SPSS, but there will be discussion of other
packages (e.g., HLM) and structural equation modeling. Although the workshop does not require any prior knowledge or experience with multilevel modeling, participants are expected to have a working knowledge of multiple regression or analysis of variance as
well as SPSS.
See schedule!
Instructor: D. Betsy McCoach
This introductory workshop on Structural Equation Modeling covers basics of path analysis, confirmatory factor analysis, and latent variable modeling. Using Mplus, participants will learn how to build, evaluate, and revise structural
equation models. Although the workshop does not require any prior knowledge or experience with SEM, participants are expected to have a working knowledge of multiple regression, as well as some experience using a statistical software program such as SPSS.
Instructors: Ann A. O'Connell
This short-course (2 days) covers extensions of mixed and hierarchical linear models for outcome variables that represent dichotomous, ordinal, multinomial, or count data. We being with a review of single-level generalized linear
models in terms of estimation, interpretation, and model fit. We then expand on this foundation to build and interpret generalized linear mixed models. Emphasis will be on model building, interpretation, comparison, and the use of analysis adjustments for
the limited nature of these kinds of dependent variables. Emphasis is on application and interpretation, with hands-on analyses and examples from the education, health, and social/behavioral sciences literature. Participant background should include regression,
analysis of variance, and some exposure to multilevel modeling. Software for examples will include HLM, SAS, and SPSS.
Instructor: D. Betsy McCoach
During this three day workshop, students will learn how to model longitudinal data using Mplus. The main focus of the workshop focuses is on fitting growth curve models in Mplus. Specifically, we will cover linear, polynomial, multiphase,
non-linear growth curve models, and multivariate growth curve models, and latent change score models for both observed variables and latent constructs.