Sensitivity of School-Performance Ratings to Scaling Decisions

DSpace/Manakin Repository

Sensitivity of School-Performance Ratings to Scaling Decisions

Citable link to this page


Title: Sensitivity of School-Performance Ratings to Scaling Decisions
Author: Ng, Hui L.; Koretz, Daniel

Note: Order does not necessarily reflect citation order of authors.

Citation: NG, Hui Leng and Daniel Koretz. 2015. Sensitivity of school-performance ratings to scaling decisions. Applied Measurement in Education 28 (4): 330-349.
Full Text & Related Files:
Abstract: Policymakers usually leave decisions about scaling the scores used for accountability to their appointed technical advisory committees and the testing contractors. However, scaling decisions can have an appreciable impact on school ratings (Briggs & Weeks, 2009). Using middle-school data from New York State, we examined the consistency of school ratings based on two scaling approaches that differed in scaling decisions that are important in high-stakes testing contexts. We found that, depending on subject, grade, and year, a switch in scaling approach led to (1) average absolute shifts in ranks of between 50 and 132 positions (median = 69), which are appreciable shifts for a listing of 1,243 schools; and (2) between 7% and 45% (average = 20%) of schools experiencing shifts in assigned performance bands, depending on the classification scheme. Further, the effect of scaling approach was larger when the raw-score distribution has more severe ceiling effect, and in these cases, it was driven primarily by the difference in the location of the highest obtainable scale score from the two scaling approaches.
Published Version: doi: 10.1080/08957347.2015.1062764
Terms of Use: This article is made available under the terms and conditions applicable to Open Access Policy Articles, as set forth at
Citable link to this page:
Downloads of this work:

Show full Dublin Core record

This item appears in the following Collection(s)


Search DASH

Advanced Search