Data on examination results from inner London schools are analysed in relation to intake achievement, pupil gender and school type. The examination achieve- ment, averaged over subjects, is studied as is achievement in the separate subjects of mathematics and English. Multilevel models are fitted, so that the variation between schools can be studied. It is shown that confidence intervals for school 'residuals' or 'effects' are wide, so that few schools can be separated reliably. In particular, no fine rank ordering of schools legitimately can be produced. A bivariate model for mathematics and English examination achievement scores is fitted. The student level variance for both subjects is shown to increase from the lowest to the highest intake achievement group, with moderately high correlation between the subjects. The paper discusses the implications of these findings for the publication of 'league tables' of school examination and test scores.
[1]
京都教育大学教育学部附属教育実践総合センター,et al.
Journal of Educational Research
,
1953
.
[2]
C. Flemming.
University of London Institute of Education
,
1955
.
[3]
M. Aitkin,et al.
Statistical Modelling Issues in School Effectiveness Studies
,
1986
.
[4]
H. Goldstein,et al.
Multilevel Models in Educational and Social Research.
,
1989
.
[5]
H. Goldstein,et al.
Differential school effectiveness
,
1989
.
[6]
J. Gray,et al.
Estimating Differences in the Examination Performances of Secondary Schools in Six LEAs: A Multi-level Approach to School Effectiveness.
,
1990
.
[7]
Bob Prosser,et al.
ML3: Software for Three-Level Analysis
,
1991
.