Psychometrics is the science of how we measure things, such as the psychological attributes of people. These psychological attributes include abilities, aptitudes, achievement, attitudes, interests, personality traits, cognitive functioning, and mental health. Psychometrics, theoretically-informed and precise measurement, is an essential component of many of the things we hold dear. Scientific advances (e.g., can I make a claim that I am measuring what I purport to measure?), educational placement decisions (e.g., should a child be placed into a gifted program?), statistical power (e.g., is my measure precise enough to suggest that X predicts Y?), and other key considerations are all affected by psychometrics. This seminar emphasizes the conceptual understanding of and the application of psychometric principles.
- Measurement and statistical concepts specific to psychometrics
- The latent variable modeling perspective
- Reliability – classical and modern approaches
- Validity – conceptual and statistical aspects
- Factor analysis – exploratory and confirmatory
- Instrument development & validation process
- Measurement bias & strategies to address bias (e.g., MIMIC models)
- Multi-group analyses & measurement invariance testing
- Missing data
- Item Response Theory: 1PL (Rasch) & 2PL & 3PL models
- How to use MPlus for psychometric analyses
An introductory 5-day seminar taught by Matthew Diemer, Ph.D. in the foundations of psychometrics. Participants should have the equivalent of a two-semester graduate-level social science statistics course sequence.
Participants will receive an electronic copy of all course materials, including lecture slides, practice datasets, software scripts, relevant supporting documentation, and recommended readings. Participants are strongly encouraged to bring their own data for “hands on” practice. Participants will also have access to a video recording of the course.
Instructor: Matthew A. Diemer Ph.D.
Matthew Diemer is a Professor in the Combined Program in Education & Psychology (CPEP) and Educational Studies programs at the University of Michigan. Diemer harnesses advanced quantitative methods to examine how young people develop critical consciousness – the capacity to reflect on, negotiate, and challenge racial, ethnic, socioeconomic and other constraints in school, college, work, and civic/political institutions. His research is currently funded by the Spencer Foundation, William T Grant Foundation, Institute for Education Sciences, National Institute of Health, National Science Foundation, and the Corporation for National and Community Service.
Diemer teaches Psychometrics and Structural Equation Modeling courses and provides statistical consultation to the campus community at the University of Michigan. He has delivered invited lectures and workshops on these and other quantitative topics domestically and internationally. He also serves as the Statistical Consultant for the Psychology of Women Quarterly.
Diemer was nominated for the “Golden Apple” teaching award and in 2019, received the Provost’s Teaching Innovation Prize for Advancing Diversity, Equity & Inclusion via Advanced Quantitative Methods, both at the University of Michigan.
Software and Computer Support
Participants need to bring a laptop computer with Wi-Fi capabilities. Students should have access to IBM SPSS, version 21.0 or higher and Mplus, version 7.1 or higher.
All statistical software used at Stats Camp with the exception of SPSS will be available, free to participants, on our SMORS (statistical modeling on remote servers) system for the duration of camp.
- Intermediate proficiency in basic statistical theory as would be gained in a 1st year graduate course.
Not required but advantageous:
- Limited experience (e.g., graduate-level course) with classical measurement theory and concepts.
No level of proficiency beyond basic awareness is assumed for skills related to:
- Advanced mathematical or statistical topics such as matrix algebra.
Below are links to seminar files for those who enrolled in the seminar. Please download these files onto your computer on the first day of the seminar. The files are password protected to respect the intellectual property rights of the instructors. By using your login information, you agree not to share your login information or the content protected by it.
Seminar files and downloads will be posted on the first day of class.