2017 Summer Quantitative Methods Series at Portland State University
This Summer Quantitative Method
Series is comprised of two-day courses on data analysis taught by nationally
recognized methodological experts. Course descriptions and more information
about instructors can be found below. Our goal is to provide additional
statistical and methodological training for research professionals from
either the private or public sector. Although course credit is not available,
graduate students are welcome and offered a discounted fee. Participants may
enroll in courses separately or in combination. Each course takes an applied
perspective with special attention given to when to use and how to implement
each technique. Statistical, mathematical, and conceptual foundations will be
included with the objective of providing a solid introduction to each area.
All courses will provide extensive software illustrations, and, unless
otherwise specified, will provide computer lab time where participants have
one-on-one assistance available when running computer examples. Some
graduate-level coursework in statistics (social science departments or
otherwise) and some experience with one or more statistical software packages
are usually assumed. Individual courses may require additional prerequisite
knowledge if indicated, however.
All classes will be held at the
Portland State University Campus located in beautiful downtown Portland, OR
between 9 am and 5 pm with an hour break for lunch. Rooms are equipped with
desktop computers for each participant, although participants are welcome to
bring their own laptops with appropriate software. Register>>
Contact Jason Newsom, Series Director, with
general questions. Contact individual instructors (email links below) with
Dynamical Systems Modeling , June 19-20, 2017
Sy-Miin Chow, PhD, Pennsylvania State University
The course will provide an overview of the concepts and theory behind dynamical
systems. Practical methods for exploring linear and nonlinear relations in
multivariate longitudinal data, as well as methods for fitting dynamical
systems models to panel and intensive longitudinal data (e.g.,
diary/experience sampling/ecological momentary assessments) will be
presented. Topics to be covered include state-space/difference equation
models, differential equation models, dynamic structural equation models, and
mixture as well as random effects extensions of these models. A variety of
examples of dynamical systems from developmental research, family studies,
psychology, and intervention science will be presented to provide some
perspectives on when dynamical systems techniques might be useful. Examples
use R and Mplus structural equation modeling
software. Students will be guided through using software programs to simulate
and develop hands-on familiarity with different types of dynamical systems,
followed by model explorations, estimation, interpretations, and diagnostics. Participants are expected to have
completed a graduate course on regression techniques and are comfortable
working with multivariate data. Experience with mixed effects modeling and R
is helpful but not required.
Sy-Miin Chow is Associate Professor in the
Department of Human Development and Family Studies at the Pennsylvania State
University. She is a winner of the Alexander von Humboldt Fellowship, the
Cattell Award from the Society of Multivariate Experimental Psychology
(SMEP), and an Early Career Award from the Psychometric Society. The focus of
her work has been on developing and testing longitudinal and dynamical
systems models and collaborating with scholars and practitioners in emotion,
aging, child development, family dynamics and prevention research to bring
new methodological developments to these areas. She has authored and edited
numerous articles and books on dynamic modeling that target a broad,
interdisciplinary audience. She has lectured and taught classes to students
with diverse backgrounds from several academic disciplines, including
Psychology, Human Development and Family Studies, Education, Business,
Kinesiology, Public Health, and Health Policy and Administration.
An Introduction to
Latent Class Analysis, June 21-22, 2017
Ph.D., University of California, Santa Barbara
This course will provide and introduction to latent class analysis
(LCA) and its application in Mplus. Topics will include a brief overview
of mixture models, including latent class, latent profile and latent
transition analysis, with the primary focus on the specification and
interpretation of latent class analysis. The course will also cover the
inclusion of auxiliary variables, covariates and distal outcomes, into LCA
models using modern methods including the BCH and 3-step methods. Modeling
extensions of the basic LCA model will be provided, with examples and Mplus syntax.
The workshop will take an applied approach–that is, specifying,
testing, and interpreting LCA model output in Mplus.
Ideally, participants should have an understanding of multiple regression and
some exposure to and familiarity with exploratory factor analysis, SEM
techniques, and categorical data analysis.
Karen Nylund-Gibson, Ph.D,
is an Associate Professor of Quantitative Research Methods in the Department
of Education at the University of California, Santa Barbara. Her research
area is on latent variable models, specifically cross-sectional and
longitudinal mixture models, class enumeration, and application of these
models in Social Science areas.
She has published many articles and book chapters on developments,
best practices, and applications of latent class analysis, latent transition
analysis, and growth mixture modeling.
Her research helps to bridge the gap between advanced statistical
literature and application of these models to substantive issues.
Item Response Theory and Modeling, June 23-24, 2017
Tenko Raykov, Ph.D., Michigan State
Item response theory (IRT) and item response modeling (IRM) are used
to investigate the item quality of tests and other measures, for measurement
development and evaluation purposes, as well as for investigating measurement
bias and group differences. This short course will discuss the measurement
theory, statistical underpinnings, and practical application of the
comprehensive IRT measurement approach.
Topics will include: testing unidimensionality
of a measuring instrument, popular unidimensional IRT models, parameter and
ability estimation in item response models, item information and test
information functions, test characteristic curves, instrument construction,
development and revision using IRT/IRM, polytomous
IRT models, an introduction to multidimensional IRT/IRM, as well as numerous
empirical illustrations of behavioral and social measurement using IRT/IRM
and latent variable modeling, and extensions of IRT/IRM. The workshop will use Mplus and Stata software. No familiarity with either of
these packages is required or expected. Free Stata licenses for the duration
of the workshop will be provided, and Mplus
examples will be possible to also do with the free demo version of Mplus.
Participants are welcome to bring laptops, but desktop laptops with
the software programs are provided. Suggested background includes familiarity
with regression and multiple regression and basic measurement concepts, such
as reliability and validity, but no extensive familiarity with behavioral or
social measurement is required. No prior exposure to IRT is needed.
Tenko Raykov, Ph.D., is
Professor of Measurement and Quantitative Methods at Michigan State
University (home page: www.msu.edu/~raykov). His research contributes to several methodological
areas with many practical applications.
These include latent variable modeling, structural equation modeling,
measurement and scale construction and development, multilevel modeling,
longitudinal data modeling, analysis of incomplete data sets, latent class
analysis, survival, event-history and duration analysis, as well as item
response theory and modeling. Dr. Raykov has
published over 150 peer-reviewed articles in widely circulated and
influential quantitative behavioral and social science journals. He has co-authored several textbooks
with Dr. G. A. Marcoulides: A First Course in
Structural Equation Modeling (2006), An Introduction to Applied Multivariate
Analysis (2008), Introduction to Psychometric Theory (2011), Basic
Statistics: An Introduction with R (2012), and Item Response Theory and
Modeling (2017). At Michigan State University, he has been teaching courses
in structural equation and latent variable modeling, psychometric theory
(behavioral and social science measurement), univariate and multivariate
statistics, item response theory, multilevel modeling, as well as units on
missing data analysis, survival analysis, latent class analysis, and
statistical software (statistics with Stata and with R).
Chris Aberson, Alex Beaujean,
Alan Agresti, Todd Bodner,
Clyde Dent, Craig Enders, David Gerbing, Ron Heck,
Nathalie Huguet, Jong Sung Kim, Rex Kline, Stephanie Lanza, Dave MacKinnon, Jack
McArdle, Jason Newsom, Jeffrey A. Smith, Mo Wang, Hyeyoung
Reviews from Past
"The instructor is extremely knowledgeable and personable. I
would highly recommend any class with this instructor."
"Really clear and well put together."
"Very comprehensive overview of the topic. Very useful."
"Very informative. I appreciated that the theoretical
constructs were connected to real data sets and output in SAS, SPSS, and
"Excellent baseline introduction."
"Well organized & nice handout booklet."
"I especially appreciated the concrete examples that were used
to illustrate each concept. It was very helpful to hear the real-world,
layman's terminology used to describe the results of models, as well."
"The reading list and online resources are great for