Wu, M. (2010). Measurement, sampling, and equating errors in large-scale assessments. Educational Measurement: Issues and Practice, 29(4), 15-27.
Wu examines the three main sources of error in large-scale assessments in education: measurement error, sampling error, and equating error. The author begins by discussing sources of error associated with assessments and then describes how to set acceptable criteria for the accuracies of assessment results. Next, Wu examines measurement error, sampling error, and equating error in detail, defining each type, why it occurs, and how to measure it. The author also includes examples throughout to illustrate each type of error and the impact on test results. Wu concludes by presenting possible solutions to help minimize or reduce error, and maintains that thorough evaluation of assessments is essential to prevent misinterpretation of results.
Analysis, Data Integrity, Quality of Assessment Data
The DataUse web site is a part of AACC
and was created and is regularly updated by CRESST
in partnership with WestEd,
and supported by the U.S. Dept. of Education.
