June 12 to June 16, 2017
Chapel Hill, North Carolina
Instructors: Dan Bauer and Doug Steinley
Software Demonstrations: R with Mplus and SPSS with Mplus
Cluster Analysis and Mixture Modeling is a five-day workshop focused on the application and interpretation of statistical techniques designed to identify subgroups within a heterogeneous population. Broadly, these techniques can be divided into: (a) cluster analysis procedures that group participants via algorithms or decision rules, and (b) latent class analysis, latent profile analysis, and other finite mixture models that discern latent subgroups of individuals using a formal statistical model. In practice, these methods are often implemented with the goal of identifying theoretically distinct subgroups (e.g., people with a liability for schizophrenia versus those without). Alternatively, they can be used as a data reduction device, to summarize prototypical patterns when working with complex multivariate data (e.g., market segments in consumer research). In recent years, an increasing focus has been on multivariate and longitudinal applications (e.g., growth mixture modeling). In this workshop we provide a comprehensive exploration of the foundations and uses of cluster analysis, latent class/profile analysis and finite mixture models, with topics ranging from introductory to advanced, and applications to both single-time point and longitudinal data, as detailed below.
Our workshop is designed for graduate students, post-doctoral fellows, faculty, and research scientists from the behavioral, social, and health sciences.
Software demonstrations for cluster analytic techniques will be provided in separate R and SPSS breakout groups (you choose which to attend). Later software demonstrations for mixture models are conducted using Mplus. While it is helpful to have some familiarity with Mplus and either R or SPSS, this is not necessary. The lectures which constitute the majority of the workshop are software-independent.
Our motivating goal is to provide an intense yet enjoyable instructional experience that focuses on a large number of both introductory and advanced topics in cluster analysis and mixture modeling. We strive to strike an equal balance between core concepts of the analytic techniques along with their practical application and interpretation when implemented with real empirical data. Our workshop is designed to provide participants with the materials and instruction needed to both develop a real understanding of cluster analysis and mixture modeling and to be able to thoughtfully apply these procedures to their own data.
In an effort to continually improve our instruction we obtain student evaluations with each course offering. Here is a sample of reviews from our 2016 Cluster Analysis and Mixture Modeling workshop:
The instructors are excellent and have an incredible understanding of this material – can’t imagine learning this material from anyone else.
It enriched my methodology “toolbox” and I feel I can do much more with my existing database as well as expanding my future research plans.
Great class! Come hungry (for knowledge and snacks!)
Excellent communication around complicated topics. A great way to accelerate knowledge!
The materials were created with such care and attention to detail and will continue to be immensely helpful as I apply this technique.
Dan Bauer and Doug Steinley co-teach the workshop and alternate lecturing throughout the day. We provide approximately 35 hours of total lecture time as well as a bound copy of the course notes and the computer demonstrations (approximately 600 pages total). Although there is not a hands-on computer lab component to this workshop, we provide extensive live demonstrations in R, SPSS, and Mplus, and we distribute the data and code for all examples. Further, participants are welcome to bring personal laptop computers to follow along with the software demonstrations or to work on their own data applications.
For examples of our course materials see sample copies of our structural equation modeling lecture notes and associated Mplus demonstration notes, as well as our multilevel modeling lecture notes and SAS software notes.
All participants also have the opportunity to sign up for individual consulting meetings on Wednesday, Thursday, or Friday.
A continental breakfast and continuous snack and beverage service are also provided each day.
Each day begins at 8:30 with a free continental-style breakfast provided at the conference center. The morning session is from 9:00 to 12:15 and includes a mid-morning break. Lunch is from 12:15 to 1:30 and attendees can select from a large number of restaurants in downtown Chapel Hill. The afternoon session continues from 1:30 to 5:00 and includes a mid-afternoon break, although the workshop ends at approximately 3:30 on Friday to allow time for travel. On Monday through Thursday, we will conduct software demonstrations from 3:30 to 5:00. For data visualization and cluster analysis demonstrations, Dan and Doug will lead separate breakout groups using SPSS and R, respectively. For mixture modeling demonstrations, we will predominantly use Mplus. Finally, we will host a happy hour on Monday at 5:00 with appetizers and drinks at The Back Bar which is located on the same floor as the lecture hall.
We are very pleased to hold our workshop in the Great Room located at the Top of the Hill Restaurant and (yes) Brewery. The Great Room is located at 100 East Franklin Street at the historic intersection of Franklin Street and Columbia Street in downtown Chapel Hill and is just steps from the campus of the University of North Carolina. The Great Room is housed in the space once occupied by the legendary Carolina Theater and is characterized by soaring ceilings, hard wood floors, red brick walls, and flowing natural light.
We have reserved a block of reduced-rate rooms at the Hampton Inn for workshop participants that will be available until May 11th or the block is sold out (if you prefer to make a reservation by phone, please indicate you are with the Curran-Bauer Analytics group). Set in the heart of Chapel Hill/Carrboro, the Hampton Inn is less than one mile from the Great Room and it is approximately a 15 minute walk from the hotel to the meeting room. Chapel Hill also offers free buses and the J-line bus route stops right in front of the hotel and then at Franklin and Columbia, the intersection nearest the Great Room.
There are also many additional local hotels available, some within walking distance and others which offer free shuttle service to and from the Great Room.
Tuition for the five-day workshop is $1795 per registrant. We offer a fixed number of reduced-price registrations of $1295 for graduate students who are actively enrolled in a recognized masters or doctoral training program. No application is necessary to qualify for the student tuition rates; simply select “student” when beginning the registration process. Confirmation of student status may be requested at a later time. We will maintain a waitlist once the student seats are filled.
We also offer a 10% reduction in total tuition when enrolling in two or more workshops. Simply proceed through the registration process and enter the code multi when prompted.
We are fortunate to have the opportunity to work in collaboration with the Society of Multivariate Experimental Psychology (SMEP) to provide a limited number of financial awards to students from under-represented groups to attend methodological workshops. These awards are made to qualifying students and post doctoral fellows with available funds of up to $1000 per student. Please see Support for Students from Underrepresented Groups to Attend Methodological Workshops for full details on both of these sources of support.
Curran-Bauer Analytics will refund registration fees for cancellations made with two weeks or more notice prior to the event. For credit card registrations, 10% will be deducted from the refund to pay transaction fees imposed by the credit card companies; there is an industry-imposed 4.95% charge to book the registration and another 4.95% to cancel the registration. For check or purchase order registrations, registration fees will be refunded in full. Registration fees are non-refundable if a cancellation is made less than two weeks before the event.
Chapter 1. Introduction
1.1 Introduction and Organization of the Workshop
1.2 Historical Context: Types and Taxonomies
1.3 Goals and Motivations: When and How Clustering can be Useful
1.4 Perspectives on Classification
1.5 Overview of General Approaches for Clustering
Chapter 2. Preliminaries: Matrix Algebra, Visualization, and Variable Selection
2.1 Brief Introduction to Matrix Algebra
2.2 Seeing Clusters: Graphical Visualization Methods
2.3 Why Variable Selection Matters
2.4 How to Decide Which Variables to Include / Exclude from Analysis
Chapter 3. Hiearchical Clustering
3.1 Motivations Behind Development and Application of Hierarchical Clustering Algorithms
3.2 Assessing (Dis)Similarity
3.3 Hierarchical Clustering Techniques: Basis and Application
3.4 Assessing Fit and Determining the Number of Clusters
Chapter 4. Non-Hierarchical Clustering
4.1 Motivations Behind Development and Application of Non-Hierarchical Clustering Algorithms
4.2 Using K-Mean Clustering to Partition Groups
4.3 Clustering with Respect to Prototypes: K-Median Clustering
Chapter 5. Finite Normal Mixture Models with One Variable
5.1 Motivations Behind Development and Application of Finite Mixture Models
5.2 Explicating the Model
5.3 How to Specify, Estimate, and Interpret the Model
5.4 Conducting Class Enumeration: Determining the Number of Mixing Components / Latent Classes
Chapter 6. Finite Normal Mixture Models with Multiple Variables
6.1 Mixtures Based on Multiple Variables: Extending to a Multivariate Normal Mixture Model
6.2 Commonly Implemented Variations in Model Specification
6.3 Applications (Including with Repeated Measures)
Chapter 7. Finite Mixture Models with Discrete or Non-Normal Indicators
7.1 Why Assuming Normality Isn’t Always Optimal
7.2 Binary and Ordinal Indicators: Latent Class Analysis
7.3 Mixtures of Non-Normal Continuous Distributions
Chapter 8. Relating Latent Classes to Predictors and Distal Outcomes
8.1 Hypothesis Testing within Finite Mixture Models
8.2 One-Step Versus Three-Step Testing Approaches
8.3 Prediction of Class Membership: Predicting Who’s in Which Class
8.4 Predicting Distal Outcomes: Determining Long-Range Outcomes of Class Membership
8.5 Latent Class Moderation Analysis: Do Predictors Have Differential Importance Across Classes?
Chapter 9. Growth Mixture Models
9.1 Heterogeneity in Change Over Time: When Theory Predicts Subgroups Follow Distinct Trajectories
9.2 Latent Class Growth Analysis / Semiparametric Groups Based Trajectory Modeling
9.3 “General” Growth Mixture Models with Random Effects
Chapter 10. Advanced Topics and Concluding Remarks
10.1 Survey of Advanced Applications of Finite Mixture Models:
– Factor Mixture Models
– Structural Equation Mixture Models
– Survival Mixture Models
– Latent Transition Analysis
10.2 Approaches for deciding on Best Structure
10.3 Summary of Decision Points, Recommendations, and Guidelines for Best Practice
Please contact us either via email or by phone (919.533.9817) if you need any additional information or have any further questions.