In Chapter 4, the author reminds us not to confuse correlation with causation. This means that just because two variables are found to have a correlation, it doesn’t mean that one necessarily “causes” the other to occur. The author also mentions in Sections 4.4 that when we find a correlation between two variables, we should be careful of “lurking variables” (p. 106).
For example, suppose a correlation is found between the number of hours a child spends on music lessons, and their overall test scores. It’s then concluded that “music lessons make children smarter”. Some possible lurking variables that may exist for this scenario are the following:
Parents that have money to spend on music lessons probably also have money to spend on better health and nutrition for their children, so this may be contributing to their better test scores. These parents may also be more educated themselves and have higher paying jobs. Therefore, they could be more inclined to motivate and encourage their child to do well in school, resulting in higher test scores. Finally, if these parents have money for music lessons, they may also have money for tutors or other resources that will help their child perform well in school. Therefore, even though there is a correlation between the number of hours spent on music lessons and the child’s test scores, it doesn’t mean that music lessons “cause” children to be smarter due to many lurking variables.
For this week’s Discussion Board post, choose one of the scenarios below and discuss some possible “lurking variables” that may exist.
a. Researchers found that adults going out to eat after 9:00 PM tend to wake up the next morning with headaches more often. They conclude that eating out after 9:00 pm causes you to be ill the next day.
b. Researchers found that children who eat breakfast tend to have better test scores than children who don’t. They conclude that eating breakfast makes children better learners.
c. Researchers observe that there is a correlation between a home’s proximity to an airport, and the number of illnesses that a person living in the home has. They conclude that airports make a person ill.
d. Researchers observe that there is a correlation between the number of glasses of red wine a person drinks per week, and the number of illnesses the person has. They conclude that drinking red wine causes a person to be healthier.
e. A correlation was found between high blood pressure and cancer rates. (People with high blood pressure were more likely to develop cancer than people with low blood pressure.) It was concluded that high blood pressure causes cancer.
f. A correlation was found between the number of A’s a student earns in high school, and their health later in life. (The more A’s, the healthier the person was.) It was concluded that getting A’s in high school causes people to be healthier later in life.