NCEE 2008-4026August 2008

Table 7.3.  Required School Sample Sizes to Detect Target Effect Sizes, for Various Random Assignment (RA) Designs

Assumes a Two-Tailed Test, a Value of .15 for the Intraclass Correlations, and a Balanced
Allocation of the Research Groups
Unit of Treatment Assignment: Other
Fixed or Random Effects
Number of Schools Required to Detect an
Impact in Standard Deviation Units of:
.20 .25 0.33
I: Students Within Sites (Schools or Districts): Site Effects Fixed
R2 = 0 14 9 5
R2 = .2 11 7 4
R2 = .5 7 5 3
R2 = .7 4 3 2
II: Classrooms Within Schools: Fixed School Effects
R2 = 0 51 33 19
R2 = .2 41 26 15
R2 = .5 26 16 9
R2 = .7 15 10 6
III: Schools: Within Districts: No Random Classroom Effects
R2 = 0 130 83 48
R2 = .2 104 66 38
R2 = .5 65 42 24
R2 = .7 39 25 14
IV: Students Within Schools: Random Site Effects
R2 = 0 42 27 15
R2 = .2 33 21 12
R2 = .5 21 13 8
R2 = .7 12 8 5
V: Classrooms Within Schools: Random School Effects
R2 = 0 79 50 29
R2 = .2 63 40 23
R2 = .5 39 25 14
R2 = .7 24 15 9
VI: Schools Within Districts: Random Classroom Effects
R2 = 0 167 107 61
R2 = .2 134 85 49
R2 = .5 83 53 31
R2 = .7 50 32 18
Note: See the text for formulas and other assumptions underlying the calculations. The figures assume that the assignment scores are normally distributed.