Multilevel Modeling for Longitudinal Data

The most interesting questions in the behavioral, social, and health sciences involve longitudinal data. Multilevel or mixed effects modeling offers a flexible and powerful framework for modeling longitudinal data. This workshop is designed to teach researchers how to use multilevel modeling to model panel and intensive longitudinal data.

Instructor:
Aidan Wright, PhD (University of Michigan)

Workshop Dates and Times:
Wednesday, June 26th, 10:00am – 3:30pm ET
Thursday, June 27th, 10:00am – 3:30pm ET
Friday, June 28th, 10:00am – 3:30pm ET

Workshop Format:
Three-Day Synchronous Online Workshop

This 3-day workshop will offer an introduction to multilevel modeling (MLM; also known as mixed effects modeling and hierarchical linear modeling) as it is applied to modeling longitudinal data. MLM is a flexible analytic framework for analyzing data that has a nested or hierarchical structure. Studies that employ a longitudinal design (e.g., panel waves, daily diaries, ecological momentary assessment) generate nested data, in the form of repeated observations nested within individuals, and therefore are usually best analyzed with MLM. The principles of MLM generalize across different forms of nesting (e.g., time-points within person; pupils within classrooms), however longitudinal data generally requires attention to specific issues (e.g., trends, cycles, temporal dependency) that make learning MLM as applied to this context advantageous.

There are many good options for learning MLM. However, what makes this course stand out is that it offers a rare hybrid of being geared towards applied researchers but not sacrificing statistical rigor. Some courses are very rigorous, but can be impenetrable for applied users. Other courses make it very easy to get going, but leave attendees without the proper fundamentals to extend beyond the courses limited examples. This course will emphasize fundamentals but do so in a way that is accessible to the applied researcher wanting to implement MLM in their own work. Additionally, there is an increasing focus on longitudinal data throughout the behavioral sciences. This course will prepare researchers to work with different types of longitudinal data, including panel data (usually 3-10 assessments over long-term) and intensive longitudinal data (usually 20 or more observations within-person over a short period of time).

What you’ll learn

  • Fundamentals - Understand the fundamental issues associated with nested data, dependent data structures, and MLM.

  • Design – Learn how to design and estimate MLMs in the popular statistical software platform R.

  • Interpretation – Develop the interpretive skills to extract valuable insights from MLMs.

  • Flexibility – Adapt to the specific modeling issues associated with different types of longitudinal data, including panel and intensive longitudinal data (e.g., as emerges from ecological momentary assessment studies)

Syllabus

Day 1:

  1. Review of the general linear model

  2. Conceptual issues with nested data structures

  3. Introduction to the basic multilevel model (MLM)

Day 2:

  1. Linear growth curve models in MLM

  2. Non-linear growth curve models

  3. Conditional models with level 2 predictors

Day 3:

  1. Level 1 predictors

  2. Cross-level interactions

Registration Options

Multilevel Modeling for Longitudinal Data

  • Professional
  • $824
  • Baseline Price for Faculty,
    Staff, and Other Professionals
  • Click Register Below
  • Trainee
  • $824 $549
  • 33% Discount for
    Students and Postdocs
  • Use code "TRAINEE" at Checkout

Combo 1: Multilevel Modeling for Longitudinal Data + Designing Ambulatory Assessment Studies

  • Professional
  • $1423 $1139
  • Baseline Price for Faculty,
    Staff, and Other Professionals
  • 20% Combination Discount
  • Click Register Below
  • Trainee
  • $1139 $759
  • 33% Discount for
    Students and Postdocs
  • 20% Combination Discount
  • Use code "TRAINEE" at Checkout

 FAQs

  • This workshop is specially designed for researchers in the behavioral and health science who want to study longitudinal processes as they play out over the long term (e.g., panel data) or short term (e.g., intensively sampled data)

  • Intermediate

  • No prior knowledge with multilevel models is necessary. However, introductory graduate level statistics is expected, especially a course on the general linear model or regression.

  • R

  • Participants will be provided with annotated example code, practice data, and example write-ups.