More General or More Specific? Implications of Specificity of Race/Ethnicity Disaggregation

• In Event: AERA Roundtable Session Friday 8:00 am Four Seasons Ballroom 4
  In Roundtable Session: Advancing Psychometric Modeling: Innovative Techniques for Educational Assessment (Table 8)

Abstract

With noncognitive measures and education outcomes data from 157,757 students, we partitioned variance between and within groups based on race/ethnicity (more general data disaggregation) versus national origin (more specific data disaggregation). ICCs of HLM two-level models were twice as large or more for groups based on national origin. We discuss implications of specificity of data disaggregation for policy and practice.

Authors

• Peter Li, University of Minnesota

• Qian Zhao, University of Minnesota