Research by Dan Ariely and Francesca Gino suggested that people were more honest in a survey when you ask them about honesty at the beginning. The problem is that the data in the analysis was likely faked. The research was over ten years ago, and Ariely suggested that the insurance company that supplied the data did something to it prior to him receiving it, but the insurance company recently stated that the data was faked after they supplied it.
In any case, there’s fake data in there somewhere. Planet Money broke it all down.
See also the analysis by Data Colada, which is why the fraud came to light.