Statistical Significance and Variance of Estimated School Fixed Effects
| Overall test score | Individual subject test scores | |||||
|---|---|---|---|---|---|---|
| Chinese | Mathematics | Physics | Chemistry | English | ||
| Individual school effects | ||||||
| F statistic | 9,217.2 | 965.0 | 16,157.9 | 404.8 | 503.0 | 111.4 |
| p-value | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| Number of observations | 2,211 | 2,211 | 2,211 | 2,211 | 2,211 | 2,211 |
| Estimated standard deviation of school effects | 13.2 | 1.9 | 5.1 | 2.7 | 2.8 | 5.4 |
| Mean score | 413.6 | 93.1 | 88.8 | 77.0 | 68.8 | 85.9 |
| Standard deviation of scores | 52.3 | 7.9 | 16.3 | 10.6 | 9.6 | 18.3 |
| Ratio of school effects standard deviation to scores standard deviation | 0.25 | 0.24 | 0.31 | 0.25 | 0.29 | 0.29 |
All regressions include selection channel effects and individual characteristics (student gender, primary school dummies, primary school test scores, parents’ education level, and parents’ income). Errors are clustered at the school level.
The standard deviation of the school fixed effects and its ratio to the standard deviation of the test scores are computed for schools from the larger of the two market segments and the corresponding students.