| Abstract: | Random assignment of students to innovative educational programs is not always possible in establishing proper and adequate control groups; therefore, it is recommended that the biomedical model of adjusted statistics designed to overcome the well-known difficulty educational investigators face when attempting to randomize subjects be adopted. The model’s utility is demonstrated by using hypothetical data for fifth grade students tested by criterion and norm referenced tests. Results indicate that the adjusted discrepancies between group statistics are considerably smaller than is indicated by inspection of raw, or unadjusted, sample values. The educational analogue of the biomedical model of adjusted rates provides a way to obtain a more accurate estimate of program success or failure when comparisons across classrooms or other units are desirable. |
