About the MCAP Summer Institute
Our week-long Summer Institute on Longitudinal Data Analysis is designed to meet the needs of 80 participants each year, welcoming individuals from all career stages and backgrounds (e.g., graduate students, post-docs, faculty, industry researchers, nonprofit and public sector workers, etc.) — all of whom are eager to enhance their knowledge in longitudinal data analysis. Our Summer Institute will be held at Purdue University in West Lafayette, IN and we will provide lodging in Purdue dorms for those selected to receive travel funding as well as per diems to cover food costs. The Summer Institute is ideal for individuals with a foundational understanding of statistics who seek to learn and apply longitudinal methods in their work. We specifically encourage applicants who are not already experts in longitudinal data analysis but who see the potential for these skills to enhance their research or professional contributions.
For Participants
- Who would benefit most from this course?
- The Summer Institute is ideal for individuals with a strong foundational understanding of statistics and regression-based methods, who seek to learn and apply longitudinal methods in their work. We specifically encourage applicants who are not already experts in longitudinal data analysis but who see the potential for these skills to enhance their research or professional contributions and who have planned or active projects using longitudinal data. Some familiarity with longitudinal data and/or analysis is useful, but not required.
- A full schedule of 2026 course topics is included in the table below
- It may also be helpful to look at the course materials from 2025 at the bottom of this page to determine if you’d benefit from the summer institute—but note we have updated topics for 2026
- When is the course?
- July 12th-July 17th, 2026
- We are accepting applications as of February 1, 2026
- Where?
- Purdue University in West Lafayette, Indiana
- How much?
- $2,000 for the Registration Fee for applicants external to Purdue; $1,500 for applicants from Purdue
- The registration fee is fully covered for those who receive scholarships (see below)
- $2,000 for the Registration Fee for applicants external to Purdue; $1,500 for applicants from Purdue
- Scholarships
- With generous support from the National Institute on Drug Abuse (R25 DA061822), we are able to provide 40 participants with full support for living expenses, registration fees, and travel costs. We aim for these funds to cover all costs of attending the summer institute.
- With generous support from the National Institute on Drug Abuse (R25 DA061822), we are also able to provide support for registration fees for an additional 30 participants. These are typically Purdue affiliated individuals and/or those local who do not require lodging or travel expenses.
- What software will we use?
- R is the officially supported statistical software for the summer institute; the slides include R code and a full set of replication files in R are provided.
- Example Stata files are also provided and instructors and TAs are happy to answer questions about using Stata
- Learning outcome goals
- 1) Expand interest and comfort applying longitudinal data to health and social science questions
- 2) Increase understanding of mastery of longitudinal data and models, including developing skills to make justified measurement and modeling decisions
- 3) Provide tools for data visualization for broad application of longitudinal analysis and dissemination of findings to interdisciplinary audiences
- How do I apply?
- We are currently accepting applications
- The deadline to apply is March 15
- The application will be used to select participants and to determine scholarship recipients
- We ask about your experience with a variety of quantitative methods and statistics topics
- We also ask for short statements about your reasons for attending the summer institute, your current level of methods/statistics expertise, longitudinal research project plans/interest, and interdisciplinary experience/interest
- Click this link to apply
- We are currently accepting applications
- Accepted for the Summer Institute?
- See the “Know Before You Go” section below for details on attending
Schedule: Summer Institute 2026
| Day | Topic | Instructor | Session Goals / Learning Objectives |
| SUNDAY | INTRODUCTION TO R | ||
| 11:30-12:00 WALC 1132 | Registration; snacks | ||
| 12:00-4:00 1:20-1:30 break 2:40-2:50 break WALC 1132 | 0: Intro to R for longitudinal data management (optional) | Dr. Katie Thompson | Introduction to the tools for efficiently managing data, unique data structures for repeated measures, tutorial for using various identifiers, transposing between long and wide formats |
| 4:30-6:30 Purdue Memorial Union (PMU) | Welcome Reception – Heavy appetizers and drinks provided Registration | ||
| MONDAY | UNDERSTANDING YOUR LONGITUDINAL DATA | ||
| 7:30-8:00 WALC 1018 | Registration; light breakfast, snacks, and coffee | ||
| 8:00-8:30 WALC 1018 | Introduction to the Summer Institute | Dr. Trent Mize & Dr. Kristine Marceau | Overview of course structure, events, and opportunities |
| 8:30-9:30 WALC 1018 9:30-9:45 break | 1. Introduction to Longitudinal Data Structures | Dr. Kristine Marceau | Long and wide data structures; combining data sources to study multilevel determinants and contextual effects |
| 9:45-10:45 WALC 1018 10:45-11:00 break | 2: Preparing your longitudinal data | Dr. Sharon Christ | Time-varying vs time-invariant variables; measured and/or measurable variables; merging data |
| 11:00-12:00 WALC 1018 | 3 Part A: Missing data in longitudinal datasets | Dr. James McCann | Sources of missing data in longitudinal studies (e.g., attrition, measure-specific), how to assess missing data patterns |
| 12:00-1:15 | Lunch Break | ||
| 1:15-2:15 WALC 1018 2:15-2:30 break | 3 Part B: Missing data in longitudinal datasets | Dr. James McCann | Introductory overview of missing data techniques available for longitudinal data |
| 2:30-4:30 WALC 1018 | 4: Data Visualization: getting to know your data | Dr. Trent Mize | Visualizing raw data (e.g., distributions, missing data, etc.). Incorporating longitudinal information in visualizations. Overview of best practices |
| 4:30-5:30 WALC 1018 | Office hours | Faculty instructors and TAs | Assignment 1: getting to know your longitudinal data; missing data considerations; visualizations |
| TUESDAY | OVERVIEW OF MODELS FOR LONGITUDINAL DATA | ||
| 8:00-8:30 WALC 1018 | Light breakfast, snacks, and coffee | ||
| 8:30-9:00 WALC 1018 | Analyses in R / overview of assignment 1 | TA | Implement the prior days topics in R. Overview assignment 1 |
| 9:00-12:00 10:30-10:45 break WALC 1018 | 5: Introduction to longitudinal data analytic methods | Dr. Rob Duncan | Broad goals and types of research questions and hypotheses applicable to large, complex longitudinal data, temporal ordering and causal inference, understand the classes of common longitudinal data analysis techniques |
| 12:00-1:15 | Lunch Break | ||
| 1:15-2:15 WALC 1018 2:15-2:25 break | 6: Longitudinal model typologies | Dr. Shawn Bauldry | Synthesizing terminology for longitudinal models; a framework for understanding estimators for longitudinal data |
| 2:25-3:25 WALC 1018 3:25-3:35 break | 7: Related models and quasi-longitudinal models | Dr. Kristine Marceau | A brief overview of related models we do not cover in depth at the summer institute: age-period-cohort analyses; models for time series data or intensive longitudinal designs; survival models. |
| 3:35-4:35 WALC 1018 | 8: Measurement error | Dr. James McCann | Overview of measurement error; specific concerns for longitudinal data; solutions |
| 4:35 – 5:30 WALC 1018 | Office hours | Faculty instructors and TAs | Assignment 2: fit core longitudinal models to your data; practice interpretation |
| WEDNESDAY | FIXED EFFECTS MODELS AND COMPLICATIONS | ||
| 8:00-8:30 WALC 1018 | Light breakfast, snacks, and coffee | ||
| 8:30-9:00 WALC 1018 | Analyses in R / overview of assignment 2 | TA | Implement the prior days topics in R. Overview assignment 2 |
| 9:00-12:00 10:15-11:30 break WALC 1018 | 9: Fixed effects models | Dr. Shawn Bauldry | Fixed effects models; time varying vs. time-invariant covariates; lagged variable predictors |
| 12:00-1:15 | Lunch Break | ||
| 1:15-4:15 2:30-2:45 break WALC 1018 4:15-4:30 break | 10: Complications: nonlinearities, categorical outcomes, moderation, and mediation | Dr. Trent Mize | Complications: modeling nonlinear effects and categorical outcome variables; analyses of moderation (interaction) and mediation (and other cross-model comparisons) |
| 4:30-5:30 WALC 1018 | Office hours | Faculty instructors and TAs | Assignment 3: fit fixed effects models to your data and interpret; add a complication to your model and interpret |
| THURSDAY | MULTILEVEL MODELS AND MARGINAL MODELING | ||
| 8:00-8:30 WALC 1018 | Light breakfast, snacks, and coffee | ||
| 8:30-9:00 WALC 1018 | Analyses in R / overview of assignment 3 | TA | Implement the prior days topics in R. Overview assignment 3 |
| 9:00-12:00 10:30-10:45 break WALC 1018 | 11: Multilevel modeling / random effects models | Dr. Kristine Marceau | Overview of multilevel and random effects models; growth curve models; cross-lagged panel models; studying multilevel determinants and contextual effect |
| 12:00-1:15 | Lunch Break | ||
| 1:15-2:15 WALC 1018 2:15-2:30 break | 12: Sampling weights | Dr. Donna Xu | When to use survey weights for analysis; issues of sample attrition |
| 2:30-4:30 WALC 1018 | 13: Marginal modeling using complex samples | Dr. Sharon Christ | Accounting for complex sampling techniques in longitudinal datasets |
| 4:30-5:30 WALC 1018 | Office hours/Open Consulting | Faculty instructors and TAs | – Assignment 4: fit a multilevel model to your data and interpret; account for complex sampling and compare results – Consult with TAs and instructors about projects you are working on |
| FRIDAY | SPECIAL TOPICS: GENE-ENVIRONMENT INTERPLAY, CAUSAL INFERENCE, AND MODEL VISUALIZATION | ||
| 8:00-8:30 WALC 1018 | Light breakfast, snacks, and coffee | ||
| 8:30-9:00 WALC 1018 | Analyses in R / overview of assignment 4 | TA | Implement the prior days topics in R. Overview assignment 4 |
| 9:00-10:00 WALC 1018 10:00-10:10 break | 14: Gene-environment interplay | Dr. Kristine Marceau | Overview of behavioral genetics theory; using polygenic scores as predictors; family-based designs; longitudinal considerations for studying gene-environment interplay |
| 10:10-11:10 WALC 1018 11:10-11:20 break | 15: Causal Inference | Dr. Trent Mize | Asking causal questions; benefits and limitations of longitudinal data for determining causality; comparing models |
| 11:20-12:20 WALC 1018 | 16 Part A: Embedded family-based designs | Dr. Kristine Marceau | Understand why many large-scale longitudinal studies include embedded family-based designs (e.g., twins/siblings; data collected on parents and children); gain the tools to avoid non-independence in these types of studies |
| 12:20-1:35 | Lunch Break | ||
| 1:35-2:35 WALC 1018 2:35-2:45 break | 16 Part B: Embedded family-based designs | Dr. Kristine Marceau | Gain an introductory understanding of options for leveraging family-based subsets to inform research questions along with resources for more in-depth instruction; causal considerations |
| 2:45-4:30 WALC 1018 | 17: Model visualization | Dr. Trenton Mize | Visualizing model results; presenting complex results in an accessible way; coefficient plots; plots of predictions and marginal effects |
| 4:30-5:30 WALC 1018 | Office hours/Open Consulting | Faculty instructors and TAs | – Assignment 5: fit a model to a family-based subsample; interpret; identify causal inference benefits and limitations of your model – Consult with TAs and instructors about projects you are working on |
| 5:30-7:30 Marriot Hall, John Purdue Room | Closing Reception – Heavy appetizers and drinks provided | ||
Featured Faculty ANd Teaching Assistants
2025 Course Materials
All course materials from the 2025 Summer Institute are included below. 2026 course materials will be posted to this site shortly before this year’s institute.