ABSTRACT
Randomization is a key, critical element of the ‘true’ experiment; random sampling and random allocation to either a control or experimental group is a key way of allowing for the very many additional uncontrolled and, hence, unmeasured, variables that may be part of the make-up of the groups in question (c.f. Slavin 2007). It is an attempt to overcome the confounding effects of exogenous and endogenous variables: the ceteris paribus condition (all other things being equal); it assumes that the distribution of these extraneous variables is more or less even and perhaps of little significance. In short it strives to address Holland’s (1986) ‘fundamental problem of causal inference’, which is that a person may not be in both a control group and an experimental group simultaneously. . . . As Schneider et al. (2007: 16) remark, because random allocation takes into account both observed and unobserved factors, controls on unobserved factors, thereby, are unnecessary. . . . If students are randomly allocated to control and experimental groups and are equivalent in all respects (by randomization) other than one group being exposed to the intervention and the other not being exposed to the intervention, then, it is argued, the researcher can attribute any different outcomes between the two groups to the effects of the intervention.
