Recall from your textbook that a correlational study investigates the strength of the relationship between two variables. It is important to remember that correlation is not equivalent to causation. That is, just because there is a relationship between two variables does not mean that one variable caused the other.
Consider the following: A study noted in your textbook found that there was a positive association between liking curly french fries and intelligence. British psychologists Kosinski and colleagues (2013) studied over 50,000 Facebook users who agreed to share their profiles and personal preferences. Kosinksi and colleagues ran correlational analyses and found associations between Facebook “likes” and personality traits. One of the more interesting findings was a strong positive correlation between intelligence and liking curly French fries and the actor Morgan Freeman’s voice. Does this mean that eating an abundance of curly French fries and listening to Morgan Freeman’s voice often results in high levels of intelligence? No. Strong correlations only indicate association, not causation! Although this is an interesting association, it would be irresponsible to suggest that any of these variables cause another based on correlational findings.
To determine causation, we must use an experimental research design. Experimental research requires the investigator to deliberately manipulate one of the factors, or variables (the independent variable), in order to determine its effect on the outcome or behavior (the dependent variable). It also requires random assignment, an experimental group, and a control group. The control group includes participants who serve as a baseline, or starting point, for comparison with the experimental group. With correlational research, we must also consider other factors that might contribute to the relationship between variables. When looking at the link between preference for french fries and intelligence perhaps there are other factors at play. For example, those who study a lot and who tend to earn higher scores on cognitive assessments, may have little time to cook and therefore prefer quick, filling foods, like french fries, in between study sessions. There are many possible explanations for possibilities this association.
Misinterpretations of correlational relationships occur frequently in the real world. Below are some examples of news headlines that may lead readers to misinterpret correlational findings and think they are cause-and-effect relationships. (Recall that cause-and-effect relationships can only be determined by means of experimental research designs.)
“Hot and Bothered: Experts Say Violent Crime Rises with the Heat”
“Does MTV’s Teen Mom Prevent or Promote Teen Pregnancy?”
“Dark Hair Dye and Chemical Relaxers Linked to Breast Cancer”
“Is Social Media to Blame for Poor Grades?”
Google one of those headlines and briefly summarize the research study on which the headline is based. Next, answer the following questions: