In a single sentence the moral is: admit that complexity always increases, first from the model you fit to the data, thence to the model you use to think about and plan about the experiment and its analysis, and thence to the true situation.

An approximate answer to the right problem is worth a good deal more than an exact answer to an approximate problem.

To be able to say that "if we change our point of view in the following way ... things are simpler" is always a gain.

Visualization is often used for evil - twisting insignificant data changes and making them look meaningful. Don't do that crap if you want to be my friend. Present results clearly and honestly. If something isn't working - those reviewing results need to know.

It's better to solve the right problem approximately than to solve the wrong problem exactly.

The best thing about being a statistician is that you get to play in everyone's backyard.

The greatest value of a picture is when it forces us to notice what we never expected to see.