In 2014, a study by Bachhuber et al. showed that, in the USA, state-level medical cannabis laws were associated with lower-than-expected opioid overdose mortality rates from 1999 to 2010. A new study by Shover et al. using the same methodology, found that in the longer period the findings reversed. In fact, in both cases, the authors underline how this kind of study should not be used to make causal claims.