NotesFAQContact Us
Collection
Advanced
Search Tips
ERIC Number: ED506850
Record Type: Non-Journal
Publication Date: 2004-May
Pages: 16
Abstractor: ERIC
Reference Count: 2
ISBN: N/A
ISSN: N/A
Assigning Adaptive NAEP Booklets Based on State Assessment Scores: A Simulation Study of the Impact on Standard Errors
Linn, Bob; McLaughlin, Don; Jiang, Tao; Gallagher, Larry
American Institutes for Research
The purpose of this simulation was to assess the improvements in estimates of standard errors that could be expected if students participating in NAEP were pre-assigned to test booklets that were adapted to their level of performance based on their state assessment scores. Students in extreme quartiles would receive one regular NAEP block and one block adapted to their performance quartile. For their adapted block, students in the lowest quartile would receive an easier block, students in the highest quartile would receive a more difficult block, and students in the middle two quartiles would receive a second "regular" NAEP block. We also considered the impact of assigning adapted blocks only to the top and bottom deciles of students, rather than to full quartiles. Results from this simulation indicate that, as predicted, assigning students "easier" test booklets based on their prior test performance can reduce standard errors in measuring students' ability levels. The reverse, however, was found to be true for "harder" booklets; in this simulation, assigning "harder" test booklets actually increased standard error estimates. Results were consistent across the four states included in this study. (Contains 7 tables, 3 footnotes, and an appendix.)
American Institutes for Research. 1000 Thomas Jefferson Street NW, Washington, DC 20007. Tel: 202-403-5000; Fax: 202-403-5001; e-mail: inquiry@air.org; Web site: http://www.air.org
Publication Type: Numerical/Quantitative Data; Reports - Evaluative
Education Level: Elementary Secondary Education
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: American Institutes for Research