ERIC Number: ED469377
Record Type: Non-Journal
Publication Date: 2001-Sep
Reference Count: N/A
Imputation of Test Scores in the National Education Longitudinal Study of 1988 (NELS:88). Working Paper Series.
Bokossa, Maxime C.; Huang, Gary G.
This report describes the imputation procedures used to deal with missing data in the National Education Longitudinal Study of 1988 (NELS:88), the only current National Center for Education Statistics (NCES) dataset that contains scores from cognitive tests given the same set of students at multiple time points. As is inevitable, cognitive test data are missing for some individuals in each test round, especially the second followup (F2). The NCES has decided to use imputation to reduce the bias caused by nonresponse. The first step was to conduct a simulation study to evaluate two different imputation procedures currently used at NCES: the model-based random imputation method (PROC IMPUTE) and a within-class random hot-deck imputation. Simulation findings confirmed that PROC IMPUTE performed better. The second step involved using PROC IMPUTE to impute missing F2 test scores in four subject areas: mathematics, reading, science, and history/citizenship/geography. Results provide end users with complete cognitive test data for both cross-sectional and longitudinal research. (Contains 18 tables, 4 figures, and 7 references.) (SLD)
Descriptors: Data Analysis, Longitudinal Studies, National Surveys, Research Methodology, Secondary Education
U.S. Department of Education, Office of Educational Research and Improvement, National Center for Education Statistics, 1990 K Street NW, Room 9048, Washington, DC 20006. For full text: htpp://www.nces.ed.gov/pubsearch/.
Publication Type: Reports - Research
Education Level: N/A
Authoring Institution: Synectics for Management Decisions, Inc., Arlington, VA.; National Center for Education Statistics (ED), Washington, DC.