Anecdotal v Empirical
I was mentioning to someone how I’d observed an increase in traffic accidents during major pattern shifts like Daylight Savings Time, and she asked me if there was a study.
It turns out there was one such study submitted as a correspondence to the New England Journal of Medicine, but it focuses specifically on the shifts into and out of DST. The results run counter to my observations, but then traffic in the Bay Area is not stationary.
It would be interesting to run controls against other pattern shifts, like Back to School week or something, but this might be harder to measure.