Northwest heat wave was statistically “impossible”

Statistics is based on a model.<p>It becomes invalid when the model becomes invalid.<p>Here, we had a new phenomena that was not included in the existing model.<p>It was not &quot;statistically impossible&quot;. Rather, it was &quot;not covered by existing statistical model&quot;.

This seems to imply that in the near future our weather models will become useless, but we won’t know when it has happened. Rohde’s Uncertainty Principle.