Table 4.
Results from meta‐regressions examining differences in effect sizes
| Moderator | (1) | (2) | (3) | (4) | (5) |
|---|---|---|---|---|---|
| Math | 0.157 [−0.022, 0.337] | 0.175* [0.007, 0.343] | 0.207* [0.0428, 0.371] | 0.188* [0.039, 0.336] | |
| QES | 0.174 [−0.016, 0.364] | 0.192* [0.015, 0.368] | 0.218* [0.0136, 0.423] | 0.242* [0.032, 0.452] | |
| Coaching of personnel | −0.056 [−0.206, 0.0937] | −0.015 [−0.172, 0.142] | |||
| CAI | −0.240* [−0.465, −0.0156] | −0.277* [−0.532, −0.023] | |||
| Incentives | −0.156 [−0.396, 0.085] | −0.151 [−0.390, 0.087] | |||
| Peer‐assisted | −0.064 [−0.258, 0.131] | −0.107 [−0.317, 0.104] | |||
| Progress monitoring | 0.020 [−0.130, 0.170] | 0.082 [−0.090, 0.255] | |||
| Small group | 0.084 [−0.111, 0.278] | 0.109 [−0.079, 0.296] | |||
| Other domain | −0.105 [−0.285, 0.075] | −0.098 [−0.289, 0.094] | |||
| General test | 0.004 [−0.137, 0.144] | ||||
| Grade | 0.013 [−0.049, 0.074] | ||||
| Duration | −0.004 [−0.010, 0.003] | ||||
| Implementation problems | 0.006 [−0.110, 0.121] | ||||
| Constant | 0.173** [0.113, 0.234] | 0.171** [0.103, 0.239] | 0.119** [0.056, 0.182] | 0.238** [0.054, 0.423] | 0.225* [0.035, 0.414] |
| Q | 300.2 | 265.2 | 264.8 | 201.8 | 183.9 |
| τ 2 | 0.040 | 0.037 | 0.038 | 0.045 | 0.050 |
| I 2 | 78.7 | 75.9 | 76.2 | 72.2 | 71.7 |
Note: Confidence intervals, based on robust standard errors, in brackets. The number of clusters is 66, the number of effect sizes is 194, and the number of student observations is 79,191 in all specifications. The number of student observations is calculated by taking the sample size for each effect size included in an estimation, which is equal to the number of students in the intervention and control group for which the effect size is calculated, and summing over effect sizes.
Abbreviations: CAI, computer‐assisted instruction; QES, quasiexperimental study.
*
p < .05.
**
p < .01.