To see pdf of full draft program, click here.
Monday – May 22, 2017
PreConference Workshop: OpenMx XSEM with Applications to Dynamical Systems Analysis
OpenMx XSEM with Applications to Dynamical Systems Analysis
Steven Boker
Laurel Hall 102
8:30 am – 5:00pm
The first half of the workshop will introduce OpenMx and the specification of simple latent variable models within R as well as provide an overview of some of its more advanced features such as full information, definition variables, parallelizing, ordinal thresholds, multiple groups, and mixture distributions. The second half of the workshop will present dynamical systems analysis as a continuous-time generalization of time series models using systems of differential equations.
Lunch is on your own. Several options are available in the Student Union.
Tuesday – May 23, 2017
Coffee, continental breakfast, and registration
7:30 AM – 8:30 AM
Laurel Hall Atrium
Welcome
8:30 AM – 8:45 AM
Laurel Hall 102
Opening Keynote: Steven Boker
8:30 AM – 10:15 AM
Laurel Hall 102
Dynamical Systems Analysis in the Context of Statistical Methods and Research Design
Steven Boker
University of Virginia
Over the past three decades, there has been a great deal of work on integrating the ideas and generative models produced in particular by mathematicians, physicists, and chemists into methods and algorithms that can be useful to test models on data from the social, behavioral, and medical sciences. Historically, Hotelling suggested in 1927 that differential equations should be used for models of change, but despaired that the problem was intractable using available tools. Stochastic differential equations and Kalman Filters were introduced in the 1950’s and 60’s. The field of dynamical systems enjoyed a burst of popularity in the 1970’s and 80’s with the co-occurring introduction of the notions of chaotic systems, fractal dimensions, and the availability of desktop computers that let one explore these generative models. There followed a period of about two decades where methods for estimating parameters of differential equations began to become better developed, but the intensive multivariate, multi-person time series required to identify such models were not yet available. Finally, in the past 10 years we have seen the emergence of widely available technology such as smart phones that can track intensively measured multivariate time series from many individuals. This talk will provide a brief history of the field dynamical systems and a way of organizing the questions we might ask of intensively time-sampled multivariate multi-person data. Some of the main dynamical systems data analytic methods available will be overviewed and placed into context of the questions for which they are best suited. A short discussion and rationale for models for self-regulating phenomena will be presented. The talk will discuss some of the problems associated with modeling nonstationary systems, why we should care, and a review of some of the methods that are in use for estimating and dealing with non-stationarity. The talk will conclude with a brief introduction to the problem of privacy preserving analytics for data on personal devices and one potential solution to this problem: distributed likelihood estimation.
Concurrent Session I: 10:30 AM – 12:00 PM
Session 1A: Symposium – Mixture models are measurement models, too! Measurement invariance and differential item functioning in latent class analysis
Laurel Hall 202
| Paper | Authors |
| Unmodeled Differential Item Functioning (DIF) in Latent Class Analysis: A Monte Carlo Simulation | Veronica Cole
Katherine Masyn Dan Bauer |
| Measurement Invariance in Multiple-Group Latent Class Analysis | Katherine Masyn
Veronica Cole Dan Bauer |
| Regression-based approaches to DIF detection in latent class models | Veronica Cole
Katherine Masyn Dan Bauer |
Session 1B: Modeling Educational Effects
Laurel Hall 205
| Paper | Authors |
| Efficacy of a Scaled-Up First Grade Reading Intervention for English Language Learners | Paulina A. Kulesz |
| Application of Cross-Classified Multiple Membership Growth Curve Modeling in a Study of the Effect of School Mobility on Students’ Academic Performance | Bess. A Rose |
| A Piecewise Latent Growth Model to Study the Effects of a College Admissions Test Overhaul | Paulina Pérez Mejias
Alberto F. Caberera |
Session 1C: Survey Research Models
Laurel Hall 206
| Paper | Authors |
| Footballs, Eigenvectors, and Psychometrics: An Outlier Detection Proposal for Likert-Type Survey Data | Allen G. Harbaugh |
| Item Response Theory and Ranking of Congressional Voting Behavior | Holmes Finch
Gregory Marchant Alicia Hazelwood |
| The Use of Topic Modeling to Analyze Open-Ended Survey Items | Holmes Finch
Maria Hernandez Finch Constance McIntosh Claire Braun |
Session 1D: Measurement and Psychometrics
Laurel Hall 301
| Paper | Authors |
| The α and the ω of Congeneric Test Theory: An Extension of Reliability and Internal Consistency to Heterogeneous Tests | Joseph F. Lucke |
| Using the Nominal IRT Model for Recency of Drug Use Items | A.R. Georgeson |
| Exploring Measurement Invariance Using CTT and IRT Techniques | Noela Haughton
Priti Signh |
Lunch –Student Union Ballroom 12:00-1:15
Concurrent Session II: 1:15 PM – 2:15 PM
Session 2A: IRT Methods and Applications
Laurel Hall 202
| Paper | Authors |
| A Conditional Joint Modeling Approach for Compensatory Multidimensional Item Response Model and Response Times | Kaiwen Man
Hong Jiao Peida Zhan Chi-Yu Huang |
| Detection of Differential Item Functioning in the Context of Clustered Data: A Comparison Study | Graham G. Rifenbark
H. Jane Rogers |
Session 2B: Mediation Models
Laurel Hall 205
| Paper | Authors |
| Multimethod Moderated Mediation Analysis using a Categorical Multigroup Design | Kaylee Litson
Christian Geiser G. Leonard Burns |
| Tools for computationally efficient power and sample size determination for mediation models | Alexander M. Shoemann
Aaron J. Boulton Stephen D. Short |
Session 2C: Intra and Inter-individual Variation Modeling
Laurel Hall 206
| Paper | Authors |
| Bayesian/Mixed-Effects Nonstationary Latent Differential Equation Models | Mauricio Garnier-Villarreal
Pascal R. Deboeck Davis K. Johnson Amber Watts |
Session 2D: Modeling Composite – Based Populations
Laurel Hall 301
| Paper | Authors |
| Modeling Composite-Based Populations Using Composite-Based Methods | Jan-Michael Becker
Edward E. Rigdon Arun Rai |
Concurrent Session III: 2:30 PM – 3:30 PM
Session 3A: Casual Inference
Laurel Hall 202
| Paper | Authors |
| The mechanics of omitted variable bias: Bias amplification and cancellation of offsetting biases | Yongnam Kim
Peter M. Steiner |
| Marginal Structural Models for Estimating the Effects of Chronic Community Violence Exposure on Youth Aggression and Depression | Traci M. Kennedy
Edward H. Kennedy |
Session 3B: Probability Index Models
Laurel Hall 205
| Paper | Authors |
| Probability Index Models | Jan De Neve |
Session 3C: Bayesian Single Case Models
Laurel Hall 206
| Paper | Authors |
| Bayesian Testing in Single-Case Research: A Forward Paradigm Shift | Tyler Hicks
Jason Travers Leslie Bross |
| Design-comparable Effect Sizes for Single-Case Research: A Bayesian Approach | Tyler Hicks
Eun Sook Kim Seang Hwane Joo Jeong Hoon Choi John Ferron Jeff Kromrey |
Session 3D: Modeling Change and Context
Laurel Hall 301
| Paper | Authors |
| Variance Estimation of Health Disparity Measures in Complex Survey Settings | Meng Qui |
| Affective Red Zones: An examination of bivariate change in context | Joel Steele
David Sbarra Emilio Ferrer |
Concurrent Session IV: 3:45 PM – 4:45 PM
Session 4A: Symposium – Applications of Multilevel Models with Latent Variables to K-12 Education
Laurel Hall 202
| Symposium | Authors |
| Different Levels of Leadership for Learning: Investigating Differences Between Teachers Individually and Collectively Using Multilevel Factor Analysis of the 2011-12 Schools and Staffing Survey | Jared Boyce
Alex J. Bowers |
| Site Section in School District Research: A Measure of Effectiveness Using Hierarchical Longitudinal Growth Models of Performance | Alex J. Bowers |
| Feasibility of Increasing Access: How Does Instructional Leadership Influence Opportunity to Learn in U.S. and Belgium? | Angela Urick
Allison Wilson Timothy G. Ford |
Session 4B: Longitudinal and Multilevel SEM
Laurel Hall 205
| Paper | Authors |
| Estimating Latent trends in Multivariate Longitudinal Data via Parafac2 with Functional and Structural Constraints | Nathaniel E. Helwig |
| Toward Multilevel Structural Equation Modeling with Latent Quadratic Effects | Joshua Pritikin |
Session 4C: Power and Program Evaluation
Laurel Hall 306
| Paper | Authors |
| The Illusion of Intended Statistical power: Avoiding Underpowered Replication Studies via Effective Sample size Planning | Samantha Anderson
Scott Maxwell Ken Kelley |
| Using Aggregate Unit Pre/Post Assessment Results Across Classrooms: A Monte Carlo Study Proof of Concept in Program Evaluation | Matthew Lavery |
Session 4D: Suppression / Non-Monotonic Effects
Laurel Hall 301
| Paper | Authors |
| Suppression Effects in Regression: The Case of Learning Strategies and Academic Achievement | Eric Loken
Xiaowen Liu |
| A New Model for Non-Monotonic Effects | David Weakliem |
Poster Session and Reception
5:00 PM – 7:00 PM
Student Union Ballroom
Wednesday – May 24, 2017
Concurrent Session V: 8:00 AM – 9:00 AM
Session 5A: Symposium – Considerations When Utilizing Indicators to Evaluate Latent-level Differences across Time and Groups
Laurel Hall 301
| Symposium | Authors |
| Longitudinal Factorial Invariance: Measuring and Modeling the Same Construct Over Time | Marilu Isiodia |
| Implications of Establishing Internal Consistency but Not Factorial Invariance on Growth Model Parameter | Marilu Isiodia |
Session 5B: Papers – Dealing with Non-normality
Laurel Hall 305
| Paper | Authors |
| Effects of Non-normality of Residuals in Hierarchical Linear Modeling | Kaiwen Man
Yating Zheng Laura Stapleton |
| Evaluation of Supplemental Samples in Longitudinal Research with Non-normal Missing Date | Jessica Mazen |
Session 5C: Evaluating Balance for Causal Inference
Laurel Hall 306
| Paper | Authors |
| Evaluating Balance for Causal Inference: An Illustration of the cobalt Package in R | Noah Greifer |
Concurrent Session VI: 9:15 AM – 10:45 AM
Session 6A: Workshop by Craig Enders: Multiple Imputation for Multilevel Data
Laurel Hall 301
| Special Workshop | Presenter |
| Multiple Imputation for Multilevel Data (Part I) | Craig Enders |
Session 6B: Graphical Methods for Understanding SEM Models
Laurel Hall 305
| Paper | Authors |
| Graphical Methods for Understanding SEM Models | Keke Lai
Samuel Green Roy Levy |
Session 6C: What the Dutch can do with prior information (and you can too)
Laurel Hall 306
| Symposium | Authors |
| Bayesian Structural Equation Models with Small Samples | Sanne Smid
Dan McNeish Rens van de Schoot |
| Using the Data Agreement Criterion to Rank Experts’ Beliefs | Duco Veen
Diedrick Stoel Rens van de Schoot |
| Testing ANOVA replications by means of the Prior Predictive p-value | Mariëlle Zondervan-Zwijnenburg
Rens van de Schoot Herbert Hoijtink |
Session 6D: SRM, Dyadic, and Social Network Analyses
Laurel Hall 106
| Paper | Authors |
| Applying Modern Methods for Missing Data Analysis to the Social Relations Model | Terrence Jorgenson |
| Modeling Parent’s Reports of Children’s Gender-Type Behavior Over Time with an Indistinguishable Dyads Common Fate Growth Model | Randi Garcia
Abbie Goldberg |
| Teacher Social Network Change over Time: How do Longitudinal Modeling Approaches Compare? | Elizabeth Dietrich
Nathan Abe Elizabeth Sanders Jessica Thompson |
Concurrent Session VII: 11:00-12:30
Session 7A: Symposium – Recent Advances in Regression Modeling with Complex Real-World Data
Laurel Hall 301
| Paper | Authors |
| Robust Finite Mixture Modeling of Censored Data Using the Multivariate Student-t Distribution | Victor Lachos |
| Leveraging Mixed and Incomplete Outcomes via a Mixed-Response Reduced Rank Regression | Kun Chen |
| Efficient Stagewise Regression for Correlated Data with Interaction Selection | Gregory Vaughan |
Session 7B: Symposium – Dynamic Methods for Multivariate Data Analyses
Laurel 305
| Paper | Authors |
| Individual as Dynamic Networks: Merging of Intraindividual variability, Network Analysis and Experience Sampling | Xiao Yang,
Nilam Ram, Scott Gest, David Lydon-Staley, David Conroy, Aaron Pincus, Peter Molenaar |
| Capturing Developmental Change in Regulation Processes using Dynamic Systems Model: Borrowing Differential Equations from Ecology | Lizbeth Benson,
Nilam Ram, Jonathan Helm, Cynthia Stifer |
| A Dynamic Model of Heart Rate Synchrony of Mother-Child Dyads in the Strange Situation | Gustav Sjobeck
Steven Boker |
| Windowed Recurrence Quantification for the Analysis of Dynamical Systems | Allison Gray
Timothy Brick |
| Windowed Spectral Coherence: A Method of Evaluating Cross-Spectral Coherence Between Nonstationary Time Series at Multiple Time-Lags | Robert G. Moulder |
Session 7C: Educational & Developmental Applications
Laurel Hall 106
| Paper | Authors |
| Self-Regulatory Climate Measures | Mwarumba Mwavita
Kathy Curry |
| Confirming the Factor Structure of the Critical Thinking Assessment Test: A Bayesian CFA Approach | Chi Hang Bryan Au
Allison Ames |
| Longitudinal Studies on Night Sleep Trajectories throughout Infancy | Shaun Goh, Daniel Goh, Teoh Oon Hoe, Seang Mei Saw, Fabian Yap, Yap Seng Chong, Anqi Qiu, Birit Brokeman |
Session 7D: Workshop- Craig Enders- Multiple Imputation for Multilevel Data
Laurel Hall 102
| Special Workshop | Presenter |
| Multiple Imputation for Multilevel Data (Part II) | Craig Enders |
Lunch – 12:30-1:30
Student Union Food Court
Keynote: 1:30 PM – 3:00 PM
Model Implied Instrumental Variables: A New Orientation to Structural Equation Models
Kenneth Bollen
Concurrent Session VIII: 3:15 PM – 4:45 PM
Session 8A: Advances in Mixture Modeling
Laurel Hall 301
| Paper | Authors |
| A framework of R-squared measures for single-level and multilevel regression mixture models | Jason Rights
Sonya Sterba |
| Methods of Covariate Inclusion in Latent Transition Analysis: A Monte Carlo Simulation Study | Ai Ye
Jeffery Harring Luke Rinne |
| Statistical Modeling of EEG Brain Mapping Data: Challenges and Opportunities | Jay Magidson |
Session 8B: Modeling Health Disparities
Laurel Hall 305
| Paper | Authors |
| Assessing health disparities in intensive longitudinal data: gender differences in Granger causality between primary care provider and emergency room usage, assessed with Medicaid insurance claims | Emil Coman
Yinghui Duan Daren Anderson |
| How to peel oranges into apples: Finding causes and effects of health disparities with difference scores built by 1-on-1 matching | Emil Coman
Helen Wu |
| A review of modern methods of estimating the size of health disparities | Emil Coman
Helen Wu |
Session 8C: Symposium – Advances in multivariate multilevel models for cross-sectional, longitudinal, and repeated cross-sectional data
Laurel Hall 306
| Symposium | Authors |
| Estimating a piecewise growth model with longitudinal data that contains individual mobility across clusters | Audrey Leroux |
| A cluster-level latent transition model for multivariate multilevel repeated cross sectional data | Katherine Masyn
Rashelle Musci Amie Bettencourt Albert Farrell |
Thursday – May 25, 2017
Post Conference workshop
Kenneth Bollen & Zachary Fisher- Model Implied instrumental variables using MIIVsem
Model Implied instrumental variables using MIIVsem
Kenneth Bollen and Zachary Fisher
This workshop will discuss more robust estimators that better represent real world conditions. Model Implied Instrumental Variable (MIIV) estimators are more robust to the approximate nature of our models and are asymptotically distribution free. In addition, they can test equation level fit so as to better localize model misspecification. The workshop will give an overview of the free R package MIIVsem. We will introduce the key ideas behind MIIV estimation; we will show how MIIVsem automates the selection of MIIVs, the estimation of coefficients and standard errors, and provides over identification tests for equations. These and other features will be introduced and illustrated with a variety of empirical examples.