The first is a single reference assignment. The second has to copy the list of references from 'newData' into '_event', possibly resizing '_event' in the process, which entails further copying.
BUT... "Premature optimization if the root of all evil." (If that doesn't ring a bell, look it up!)
The semantic difference is probably more important in most cases. In the first you are just referencing the data provided to 'set' - if the calling code later changes it, it is changed in '_events' too (because '_events' IS 'newData'). This could cause dangerous side effects, if it wasn't intended.
In the second, subsequent changes to 'newData' are not reflected as changes to '_events' because '_events' is a copy of new data. Which is right is down to the semantics of your application. The same applies, in reverse, if you have a 'get' matching this 'set'.
If you are going to be updating only the contents of '_events' rather than changing what it references, you should also consider making it final.
Hmmm. I just noticed that '_data' is only mentioned once in your example. I have assumed above that '_data' and '_events' are the same thing (i.e. it is a typo) - otherwise why would you mention '_data' at all?