[PAST EVENT] Workshop: Equity-Informed Measurement (Session II)

October 29, 2021
9:30am - 12:30pm
School of Education, Zoom
301 Monticello Ave
Williamsburg, VA 23185Map this location
Access & Features
  • Registration/RSVP

Join Dr. Matthew Diemer from the University of Michigan for a two-day virtual workshop focused on using measurement as a tool to advance equity. This two-day workshop builds, so we encourage participants to attend both sessions: 

About the Workshop

Measurement has a problematic history and has often been used to reinforce and perpetuate racial, socioeconomic, gendered, and other group-based inequities and hierarchies. This workshop instead offers a perspective on measurement as a tool to advance equity. We can repurpose measurement, despite these histories, as a way to address, identify, and remediate racial bias in measurement (for example) as well as to communicate to psychometricians via technical language and concepts.  

This two-day workshop therefore centers equity in understanding and learning to apply measurement. This workshop offers latent variables as an overarching perspective to understand measurement concepts, principles, and techniques. Specifically, this workshop will cover: (a) confirmatory factor analyses, or CFA, and (b) MIMIC models. These techniques provide a powerful way to identify and remediate bias in measurement, as well as to make claims about equity-informed measurement that are supported by psychometric principles. The motivating examples in the workshop center race and critical perspectives, in order to articulate an asset- and equity-informed approach.

Syntax will be provided for example models in Mplus. I require downloading the free demo version of Mplus (www.statmodel.com) prior to the start of the workshop, which we will use during the ‘hands on’ portion of each session. Attendees who have access to the full (paid) version of Mplus are encouraged to use the full version. Attendees should have a copy of SPSS, Stata, R or some other package that they are familiar with, for (minimal) data manipulation. 


Julie Tucker, [[jstucker]]