In April 2002 the American Journal of Political Science published a research report, “Correlation not Causation: The Relationship Between Personality Traits and Political Ideologies.” It was written by a group of researchers from Virginia Commonwealth University who studied the link between political beliefs and personality traits. They found that the two were connected, and that the connection could be attributed to genes. Along the way, they noticed that certain personality traits were associated with liberals and others with conservatives.
They were particularly interested in a collection of personality features—what psychiatrists call a personality constellation—called P. The authors noted that people with low P scores are more likely to be “altruistic, well socialized, empathic, and conventional.” By contrast, people who have high P scores are “manipulative, tough-minded, and practical,” and present characteristics such as “risk-taking, sensation-seeking, impulsivity, and authoritarianism.” They concluded, “As such, we expect higher P scores to be related to a more conservative political attitude.”
What they predicted was exactly what they found. The stereotypes, they said, were true: conservatives tend to be impulsive and authoritarian while liberals tend to be well socialized and generous. But in science, when you find just what you expect, it can be a red flag. And in January 2016, fourteen years after the original report, the journal published a retraction:

The authors regret that there is an error in the published version of “Correlation not Causation: The Relationship Between Personality Traits and Political Ideologies.” The interpretation of the coding . . . was exactly reversed.