Fred Rogers wanted to test a new “sing-along" method to teach math to fourth graders (e.g. "I Love to Multiply to the tune of God Bless America). He used the sing-along method in his first
period class. His sixth period students continued solving math problems with the old method. At
the end of the term, Mr. Rogers found that the first period class scored significantly lower than
the sixth period class on a mathematics achievement test. He concluded that his sing-along
method was a total failure.
1. Are the researcher's conclusions warranted (yes/no)?
2. Name the independent variable(s):
3. Name the dependent variable(s):
4. Name the confounded variable(s):
5. What is one method to "unconfound" the experiment?
1. Are the researcher's conclusions warranted (yes/no)?
No, due to the confounding variables.
2. Name the independent variable(s):
The independent variable is the type of instruction.
3. Name the dependent variable(s):
Performance on a math achievement test
4. Name the confounded variable(s):
The dependent variable, which is performance on the test. The two groups might not have equivalent ability or knowledge when the study was begun. There could be systematic sampling bias; for example, if the first-period class “happened” to be together because of a high-level class that conflicted with the 6th-period time slot.
5. What is one method to "unconfound" the experiment?
The teacher could give both a pre-test and a post-test. The dependent variable could then be the difference between the two scores rather than the raw score on the post-test. This would control for different levels of knowledge when the study was begun. It would NOT control for different aptitudes for learning math in the two groups, since a higher-ability group would be likely to learn the material faster regardless of the teaching method. To control for this, the teacher would have to separate each class randomly into two groups, and use one group from each class as experimental and control.