Klahr and Nigam (2004) studied the question of whether learning by "discovery" is better than direct instruction. Two groups of third- and fourth-grade children were asked to learn how to create simple experiments in which there is no confounding between explanatory variables. One group designed two experiments and then received direct instruction on good and bad experiments and the differences between them. A second group was allowed to explore on their own and come up with their own ways of designing unconfounded experiments. In an assessment phase, children were graded as "masters" or "nonmasters" of design skills. The results showed that 77% of the 52 children receiving direct instruction became masters, whereas only 23% of the 52 discovery children did so. How would you analyze these data?