When can fresh or new statistics cause a problem? Ever?

Database
The Teradata Database channel includes discussions around advanced Teradata features such as high-performance parallel database technology, the optimizer, mixed workload management solutions, and other related technologies.

When can fresh or new statistics cause a problem? Ever?

I've got users that swear that they've seen cases where fresh statistics have caused performance regressions. However they can't provide much background as to when or how this has happened in the past. Has anyone here had any experience with this happenining on any release post 12.0?