Estimating Standard Errors for School PAAC's in Generalizability Theory.
Saved in:
| Title: | Estimating Standard Errors for School PAAC's in Generalizability Theory. |
|---|---|
| Language: | English |
| Authors: | Lee, Guemin, Fitzpatrick, Anne R., Ito, Kyoko |
| Peer Reviewed: | N |
| Page Count: | 27 |
| Publication Date: | 2001 |
| Document Type: | Numerical/Quantitative Data Reports - Research Speeches/Meeting Papers |
| Descriptors: | Academic Achievement, Cutting Scores, Elementary Education, Elementary School Students, English, Error of Measurement, Estimation (Mathematics), Generalizability Theory, Junior High School Students, Language Arts, Mathematics Tests, Performance Factors |
| Geographic Terms: | U.S.; California |
| Abstract: | School test performance is commonly summarized in terms of the percentage of students at or above a cut score (PAAC) that has been set on a test. Two approaches to estimating the standard errors for school PAACs were examined in this study: conditional standard errors and overall standard errors. The tests used were English language arts and mathematics tests administered in 1999 to students in grades 4 and 8 as part of a large statewide assessment. About 150 schools were randomly selected for the analyses. The results indicate that: (1) the conditional standard error appears to follow a quadratic pattern as a function of PAAC regardless of school size; (2) the quadratic shape is substantial when school size is small; and (3) there is distinct similarity between overall and conditional standard errors when they are conditioned on school size. Several feasible ways of reporting standard error information for school PAACs are also presented. (Contains 6 tables, 6 figures, and 13 references.) (Author/SLD) |
| Notes: | Paper presented at the Annual Meeting of the American Educational Research Association (Seattle, WA, April 10-14, 2001). |
| Journal Code: | RIEAUG2001 |
| Entry Date: | 2001 |
| Accession Number: | ED451257 |
| Database: | ERIC |
| Abstract: | School test performance is commonly summarized in terms of the percentage of students at or above a cut score (PAAC) that has been set on a test. Two approaches to estimating the standard errors for school PAACs were examined in this study: conditional standard errors and overall standard errors. The tests used were English language arts and mathematics tests administered in 1999 to students in grades 4 and 8 as part of a large statewide assessment. About 150 schools were randomly selected for the analyses. The results indicate that: (1) the conditional standard error appears to follow a quadratic pattern as a function of PAAC regardless of school size; (2) the quadratic shape is substantial when school size is small; and (3) there is distinct similarity between overall and conditional standard errors when they are conditioned on school size. Several feasible ways of reporting standard error information for school PAACs are also presented. (Contains 6 tables, 6 figures, and 13 references.) (Author/SLD) |
|---|
